Hardware6
Apple M1 Max
115 runsBest decode · TG128 @ 1 ctx
366.4tok/s
Best prefill · PP512
5,884tok/s
Apple M3 Ultra
104 runsBest decode · TG128 @ 1 ctx
488.1tok/s
Best prefill · PP512
12,301tok/s
NVIDIA GB10
94 runsBest decode · TG128 @ 1 ctx
456tok/s
Best prefill · PP512
49,488tok/s
Apple M4 Max
79 runsBest decode · TG128 @ 1 ctx
573.4tok/s
Best prefill · PP512
10,006tok/s
Apple M4 Pro
67 runsBest decode · TG128 @ 1 ctx
401.9tok/s
Best prefill · PP512
5,025tok/s
unknown
41 runsBest decode · TG128 @ 1 ctx
450.2tok/s
Best prefill · PP512
51,746tok/s
Badges6
Record1
Pioneer1
Volume1
Coverage3
257 decode records
Fastest result in a tested configuration
Record
First run
Submitted a benchmark report
Pioneer
40 runs
Sustained contributor
Volume
Model explorer
39 models covered
Coverage
Hardware explorer
6 devices covered
Coverage
Multi-backend
cuda + metal
Coverage
Submissions500
Sort by
Order
Prefill size
500 submissions · PP512 selected
| Model / runtime / format | Device | Backend | Report | |||
|---|---|---|---|---|---|---|
Qwen3.5-35B-A3B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 111.4 tok/s TG128 @ 1 ctx | 2,310 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 136.6 tok/s TG128 @ 1 ctx | 2,329 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 38.3 tok/s TG128 @ 1 ctx | 410 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 228.6 tok/s TG128 @ 1 ctx | 5,433 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 227.4 tok/s TG128 @ 1 ctx | 5,418 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 313.4 tok/s TG128 @ 1 ctx | 5,478 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 312.3 tok/s TG128 @ 1 ctx | 5,495 tok/s PP512 | ||
gemma-3-1b-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 331.4 tok/s TG128 @ 1 ctx | 10,125 tok/s PP512 | ||
Qwen3-0.6B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 488.1 tok/s TG128 @ 1 ctx | 12,301 tok/s PP512 | ||
gemma-3-1b-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 262.3 tok/s TG128 @ 1 ctx | 9,865 tok/s PP512 | ||
Qwen3-0.6B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 418.6 tok/s TG128 @ 1 ctx | 11,505 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 415.1 tok/s TG128 @ 1 ctx | 8,900 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 314.9 tok/s TG128 @ 1 ctx | 5,751 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 311.3 tok/s TG128 @ 1 ctx | 5,484 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 356.8 tok/s TG128 @ 1 ctx | 9,006 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 305.2 tok/s TG128 @ 1 ctx | 5,442 tok/s PP512 | ||
Qwen3-1.7B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 246.8 tok/s TG128 @ 1 ctx | 5,666 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 170.9 tok/s TG128 @ 1 ctx | 2,591 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 232.5 tok/s TG128 @ 1 ctx | 5,415 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 230.2 tok/s TG128 @ 1 ctx | 5,282 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 203.1 tok/s TG128 @ 1 ctx | 3,306 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 160.2 tok/s TG128 @ 1 ctx | 2,541 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 161.0 tok/s TG128 @ 1 ctx | 2,546 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 142.7 tok/s TG128 @ 1 ctx | 8,609 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 159.9 tok/s TG128 @ 1 ctx | 3,309 tok/s PP512 | ||
Qwen3-4B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 122.5 tok/s TG128 @ 1 ctx | 2,542 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 122.0 tok/s TG128 @ 1 ctx | 2,550 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 121.5 tok/s TG128 @ 1 ctx | 2,548 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 131.3 tok/s TG128 @ 1 ctx | 1,435 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 98.8 tok/s TG128 @ 1 ctx | 3,540 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 118.3 tok/s TG128 @ 1 ctx | 1,398 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 125.7 tok/s TG128 @ 1 ctx | 1,430 tok/s PP512 | ||
gemma-4-E2B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 122.4 tok/s TG128 @ 1 ctx | 8,469 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 81.7 tok/s TG128 @ 1 ctx | 1,427 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 78.1 tok/s TG128 @ 1 ctx | 1,423 tok/s PP512 | ||
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 78.0 tok/s TG128 @ 1 ctx | 3,503 tok/s PP512 | ||
Qwen3-8B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 75.9 tok/s TG128 @ 1 ctx | 1,375 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 38.4 tok/s TG128 @ 1 ctx | 409 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 84.5 tok/s TG128 @ 1 ctx | 2,404 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 137.8 tok/s TG128 @ 1 ctx | 2,330 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 139.2 tok/s TG128 @ 1 ctx | 2,315 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 136.1 tok/s TG128 @ 1 ctx | 2,311 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 76.7 tok/s TG128 @ 1 ctx | 2,306 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 99.3 tok/s TG128 @ 1 ctx | 2,289 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 113.4 tok/s TG128 @ 1 ctx | 2,312 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 60.3 tok/s TG128 @ 1 ctx | 948 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 63.9 tok/s TG128 @ 1 ctx | 945 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 106.5 tok/s TG128 @ 1 ctx | 954 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 110.7 tok/s TG128 @ 1 ctx | 957 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 103.5 tok/s TG128 @ 1 ctx | 1,720 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 105.9 tok/s TG128 @ 1 ctx | 1,716 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 131.1 tok/s TG128 @ 1 ctx | 2,204 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M4 Max | Metal | 201.8 tok/s TG128 @ 1 ctx | 3,900 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M4 Max | Metal | 202.8 tok/s TG128 @ 1 ctx | 3,918 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 122.5 tok/s TG128 @ 1 ctx | 1,723 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 123.1 tok/s TG128 @ 1 ctx | 1,723 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M4 Max | Metal | 298.8 tok/s TG128 @ 1 ctx | 3,966 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M4 Max | Metal | 303.2 tok/s TG128 @ 1 ctx | 3,949 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 188.3 tok/s TG128 @ 1 ctx | 2,109 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 138.5 tok/s TG128 @ 1 ctx | 2,059 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 138.3 tok/s TG128 @ 1 ctx | 2,079 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 18.1 tok/s TG128 @ 1 ctx | 144 tok/s PP512 | ||
Qwen3.8-27B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 18.1 tok/s TG128 @ 1 ctx | 144 tok/s PP512 | ||
Qwen3.6-35B-A3B-cuda-q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 54.7 tok/s TG128 @ 1 ctx | 3,156 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 91.4 tok/s TG128 @ 1 ctx | 880 tok/s PP512 | ||
Qwen3.5-35B-A3B-cuda-q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 54.3 tok/s TG128 @ 1 ctx | 3,663 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 89.7 tok/s TG128 @ 1 ctx | 857 tok/s PP512 | ||
Qwen3.6-27B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 10.9 tok/s TG128 @ 1 ctx | 142 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 8.3 tok/s TG128 @ 1 ctx | 1,722 tok/s PP512 | ||
Qwen3.6-27B-cuda-q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 7.5 tok/s TG128 @ 1 ctx | 1,700 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 11.0 tok/s TG128 @ 1 ctx | 142 tok/s PP512 | ||
Qwen3.6-35B-A3B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 73.1 tok/s TG128 @ 1 ctx | 3,919 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M4 Pro | Metal | 173.9 tok/s TG128 @ 1 ctx | 1,810 tok/s PP512 | ||
Qwen3.5-35B-A3B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 78.0 tok/s TG128 @ 1 ctx | 4,334 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 104.8 tok/s TG128 @ 1 ctx | 2,765 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 104.8 tok/s TG128 @ 1 ctx | 2,937 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M4 Pro | Metal | 112.7 tok/s TG128 @ 1 ctx | 1,793 tok/s PP512 | ||
Qwen3.6-27B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 12.3 tok/s TG128 @ 1 ctx | 1,729 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 71.8 tok/s TG128 @ 1 ctx | 871 tok/s PP512 | ||
Qwen3.8-27B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 13.1 tok/s TG128 @ 1 ctx | 849 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 13.1 tok/s TG128 @ 1 ctx | 395 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M4 Pro | Metal | 113.4 tok/s TG128 @ 1 ctx | 1,812 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 70.5 tok/s TG128 @ 1 ctx | 828 tok/s PP512 | ||
Qwen3.5-2B-cuda-q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 110.5 tok/s TG128 @ 1 ctx | 17,866 tok/s PP512 | ||
Qwen3.5-2B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 148.7 tok/s TG128 @ 1 ctx | 18,297 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 182.5 tok/s TG128 @ 1 ctx | 6,875 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M4 Pro | Metal | 172.3 tok/s TG128 @ 1 ctx | 1,835 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 188.6 tok/s TG128 @ 1 ctx | 2,105 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 183.2 tok/s TG128 @ 1 ctx | 6,988 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 73.9 tok/s TG128 @ 1 ctx | 1,677 tok/s PP512 | ||
gpt-oss-20b-MXFP4 BaseRTmxfp4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 72.3 tok/s TG128 @ 1 ctx | 737 tok/s PP512 | ||
gpt-oss-20b-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 73.2 tok/s TG128 @ 1 ctx | 729 tok/s PP512 | ||
gpt-oss-20b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 78.6 tok/s TG128 @ 1 ctx | 731 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 31.9 tok/s TG128 @ 1 ctx | 392 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 33.6 tok/s TG128 @ 1 ctx | 391 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 56.1 tok/s TG128 @ 1 ctx | 727 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 56.0 tok/s TG128 @ 1 ctx | 726 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 77.8 tok/s TG128 @ 1 ctx | 727 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 142.2 tok/s TG128 @ 1 ctx | 1,790 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 77.8 tok/s TG128 @ 1 ctx | 725 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 80.3 tok/s TG128 @ 1 ctx | 1,669 tok/s PP512 | ||
Qwen3-8B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 59.6 tok/s TG128 @ 1 ctx | 942 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 113.4 tok/s TG128 @ 1 ctx | 1,809 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 112.3 tok/s TG128 @ 1 ctx | 1,812 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 103.0 tok/s TG128 @ 1 ctx | 959 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 172.5 tok/s TG128 @ 1 ctx | 1,815 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 71.6 tok/s TG128 @ 1 ctx | 828 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 71.7 tok/s TG128 @ 1 ctx | 877 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 60.6 tok/s TG128 @ 1 ctx | 856 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 64.5 tok/s TG128 @ 1 ctx | 893 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 11.0 tok/s TG128 @ 1 ctx | 143 tok/s PP512 | ||
Qwen3.6-27B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 11.0 tok/s TG128 @ 1 ctx | 142 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 44.5 tok/s TG128 @ 1 ctx | 876 tok/s PP512 | ||
muse-glimmer-30B-kquant-dynamic BaseRTpassthrough_gguf The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 14.3 tok/s TG128 @ 1 ctx | 135 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 91.5 tok/s TG128 @ 1 ctx | 858 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 92.6 tok/s TG128 @ 1 ctx | 880 tok/s PP512 | ||
muse-glimmer-30B-kquant-17gb BaseRTpassthrough_gguf The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 17.3 tok/s TG128 @ 1 ctx | 140 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 109.1 tok/s TG128 @ 1 ctx | 853 tok/s PP512 | ||
Qwen3.8-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 18.1 tok/s TG128 @ 1 ctx | 143 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 87.5 tok/s TG128 @ 1 ctx | 902 tok/s PP512 | ||
Qwen3.5-122B-A10B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 33.2 tok/s TG128 @ 1 ctx | 1,085 tok/s PP512 | ||
gpt-oss-120b-MXFP4 BaseRTmxfp4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 42.2 tok/s TG128 @ 1 ctx | 2,631 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 86.5 tok/s TG128 @ 1 ctx | 903 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 51.6 tok/s TG128 @ 1 ctx | 870 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 18.0 tok/s TG128 @ 1 ctx | 143 tok/s PP512 | ||
gpt-oss-120b-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 35.5 tok/s TG128 @ 1 ctx | 2,623 tok/s PP512 | ||
gpt-oss-120b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 39.9 tok/s TG128 @ 1 ctx | 1,903 tok/s PP512 | ||
gpt-oss-20b-MXFP4 BaseRTmxfp4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 75.9 tok/s TG128 @ 1 ctx | 891 tok/s PP512 | ||
gpt-oss-20b-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 74.8 tok/s TG128 @ 1 ctx | 867 tok/s PP512 | ||
gpt-oss-20b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 81.3 tok/s TG128 @ 1 ctx | 884 tok/s PP512 | ||
Qwen3-8B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 38.2 tok/s TG128 @ 1 ctx | 501 tok/s PP512 | ||
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 51.3 tok/s TG128 @ 1 ctx | 1,369 tok/s PP512 | ||
Qwen3.6-35B-A3B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 54.5 tok/s TG128 @ 1 ctx | 3,182 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 38.7 tok/s TG128 @ 1 ctx | 508 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 40.7 tok/s TG128 @ 1 ctx | 510 tok/s PP512 | ||
Qwen3.5-35B-A3B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 54.3 tok/s TG128 @ 1 ctx | 3,647 tok/s PP512 | ||
Qwen3-8B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 31.5 tok/s TG128 @ 1 ctx | 393 tok/s PP512 | ||
gemma-4-E2B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 89.6 tok/s TG128 @ 1 ctx | 4,386 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 63.5 tok/s TG128 @ 1 ctx | 511 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 7.5 tok/s TG128 @ 1 ctx | 1,701 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 49.5 tok/s TG128 @ 1 ctx | 7,382 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 60.2 tok/s TG128 @ 1 ctx | 507 tok/s PP512 | ||
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 44.1 tok/s TG128 @ 1 ctx | 1,072 tok/s PP512 | ||
Qwen3.6-27B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 7.5 tok/s TG128 @ 1 ctx | 1,700 tok/s PP512 | ||
gemma-4-E2B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 83.8 tok/s TG128 @ 1 ctx | 3,633 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 55.7 tok/s TG128 @ 1 ctx | 394 tok/s PP512 | ||
gemma-4-26B-A4B-it-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 40.5 tok/s TG128 @ 1 ctx | 6,005 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 75.1 tok/s TG128 @ 1 ctx | 1,383 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 66.4 tok/s TG128 @ 1 ctx | 512 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 52.4 tok/s TG128 @ 1 ctx | 399 tok/s PP512 | ||
Qwen3.6-35B-A3B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 73.3 tok/s TG128 @ 1 ctx | 3,884 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 71.6 tok/s TG128 @ 1 ctx | 919 tok/s PP512 | ||
Qwen3.5-35B-A3B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 92.6 tok/s TG128 @ 1 ctx | 3,995 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 86.3 tok/s TG128 @ 1 ctx | 2,899 tok/s PP512 | ||
Qwen3.6-27B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 11.5 tok/s TG128 @ 1 ctx | 1,711 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 71.4 tok/s TG128 @ 1 ctx | 923 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 90.6 tok/s TG128 @ 1 ctx | 2,898 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 68.8 tok/s TG128 @ 1 ctx | 1,101 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 99.1 tok/s TG128 @ 1 ctx | 7,437 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 58.5 tok/s TG128 @ 1 ctx | 392 tok/s PP512 | ||
Qwen3-4B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 71.2 tok/s TG128 @ 1 ctx | 918 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 77.7 tok/s TG128 @ 1 ctx | 3,911 tok/s PP512 | ||
Qwen3.8-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 13.1 tok/s TG128 @ 1 ctx | 1,713 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 103.7 tok/s TG128 @ 1 ctx | 4,780 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 88.6 tok/s TG128 @ 1 ctx | 1,239 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 80.8 tok/s TG128 @ 1 ctx | 4,718 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 14.1 tok/s TG128 @ 1 ctx | 385 tok/s PP512 | ||
Qwen3-4B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 55.8 tok/s TG128 @ 1 ctx | 725 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 118.2 tok/s TG128 @ 1 ctx | 4,523 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 89.4 tok/s TG128 @ 1 ctx | 925 tok/s PP512 | ||
gemma-4-26B-A4B-it-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 44.1 tok/s TG128 @ 1 ctx | 6,188 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 44.0 tok/s TG128 @ 1 ctx | 6,112 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 90.4 tok/s TG128 @ 1 ctx | 922 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 70.7 tok/s TG128 @ 1 ctx | 934 tok/s PP512 | ||
gpt-oss-20b-MXFP4 BaseRTmxfp4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 59.9 tok/s TG128 @ 1 ctx | 4,448 tok/s PP512 | ||
gpt-oss-20b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 74.8 tok/s TG128 @ 1 ctx | 4,356 tok/s PP512 | ||
gpt-oss-20b-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 51.5 tok/s TG128 @ 1 ctx | 4,412 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 121.8 tok/s TG128 @ 1 ctx | 3,736 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 108.6 tok/s TG128 @ 1 ctx | 1,238 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 94.7 tok/s TG128 @ 1 ctx | 934 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 140.5 tok/s TG128 @ 1 ctx | 2,068 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 25.5 tok/s TG128 @ 1 ctx | 7,170 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 30.2 tok/s TG128 @ 1 ctx | 7,662 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 139.1 tok/s TG128 @ 1 ctx | 2,070 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 89.3 tok/s TG128 @ 1 ctx | 734 tok/s PP512 | ||
gemma-4-E2B-it-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 86.9 tok/s TG128 @ 1 ctx | 19,183 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 49.7 tok/s TG128 @ 1 ctx | 1,467 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 104.3 tok/s TG128 @ 1 ctx | 926 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 51.6 tok/s TG128 @ 1 ctx | 7,333 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 71.8 tok/s TG128 @ 1 ctx | 3,593 tok/s PP512 | ||
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 76.3 tok/s TG128 @ 1 ctx | 2,497 tok/s PP512 | ||
gemma-4-E2B-it-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 76.0 tok/s TG128 @ 1 ctx | 17,897 tok/s PP512 | ||
Qwen3-1.7B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 125.3 tok/s TG128 @ 1 ctx | 1,819 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 54.0 tok/s TG128 @ 1 ctx | 7,566 tok/s PP512 | ||
gemma-4-E2B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 131.8 tok/s TG128 @ 1 ctx | 7,481 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 53.3 tok/s TG128 @ 1 ctx | 11,490 tok/s PP512 | ||
Qwen3-1.7B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 153.6 tok/s TG128 @ 1 ctx | 2,210 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 112.1 tok/s TG128 @ 1 ctx | 2,557 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 54.9 tok/s TG128 @ 1 ctx | 11,378 tok/s PP512 | ||
Llama-3.2-3B-Instruct-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 67.1 tok/s TG128 @ 1 ctx | 15,528 tok/s PP512 | ||
Qwen3-4B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 104.7 tok/s TG128 @ 1 ctx | 1,719 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 176.8 tok/s TG128 @ 1 ctx | 2,691 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 232.7 tok/s TG128 @ 1 ctx | 3,357 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 68.2 tok/s TG128 @ 1 ctx | 14,830 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 131.9 tok/s TG128 @ 1 ctx | 11,398 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 188.7 tok/s TG128 @ 1 ctx | 2,102 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 72.8 tok/s TG128 @ 1 ctx | 10,965 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 172.0 tok/s TG128 @ 1 ctx | 1,833 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 72.2 tok/s TG128 @ 1 ctx | 11,179 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 171.1 tok/s TG128 @ 1 ctx | 7,757 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 87.8 tok/s TG128 @ 1 ctx | 14,593 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 184.7 tok/s TG128 @ 1 ctx | 2,096 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 163.4 tok/s TG128 @ 1 ctx | 1,743 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 190.7 tok/s TG128 @ 1 ctx | 1,822 tok/s PP512 | ||
Qwen3.5-2B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 109.1 tok/s TG128 @ 1 ctx | 17,984 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 89.4 tok/s TG128 @ 1 ctx | 2,842 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 220.2 tok/s TG128 @ 1 ctx | 2,230 tok/s PP512 | ||
Llama-3.2-3B-Instruct-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 107.0 tok/s TG128 @ 1 ctx | 15,281 tok/s PP512 | ||
Qwen3-1.7B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 220.9 tok/s TG128 @ 1 ctx | 4,030 tok/s PP512 | ||
Qwen3.5-2B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 149.2 tok/s TG128 @ 1 ctx | 18,209 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 199.0 tok/s TG128 @ 1 ctx | 2,679 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 168.2 tok/s TG128 @ 1 ctx | 37,392 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 319.8 tok/s TG128 @ 1 ctx | 6,014 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 238.3 tok/s TG128 @ 1 ctx | 3,348 tok/s PP512 | ||
Llama-3.2-1B-Instruct-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 169.5 tok/s TG128 @ 1 ctx | 36,737 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 181.7 tok/s TG128 @ 1 ctx | 6,739 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 179.0 tok/s TG128 @ 1 ctx | 6,868 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 320.1 tok/s TG128 @ 1 ctx | 4,079 tok/s PP512 | ||
gemma-3-1b-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 172.0 tok/s TG128 @ 1 ctx | 3,428 tok/s PP512 | ||
gemma-3-1b-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 167.3 tok/s TG128 @ 1 ctx | 4,116 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 201.4 tok/s TG128 @ 1 ctx | 7,218 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 371.4 tok/s TG128 @ 1 ctx | 6,067 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | unknown | CUDA | 191.9 tok/s TG128 @ 1 ctx | 34,471 tok/s PP512 | ||
Qwen3-0.6B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 298.7 tok/s TG128 @ 1 ctx | 4,845 tok/s PP512 | ||
Qwen3-0.6B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 307.9 tok/s TG128 @ 1 ctx | 5,884 tok/s PP512 | ||
gemma-3-1b-it-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 186.3 tok/s TG128 @ 1 ctx | 33,276 tok/s PP512 | ||
gemma-3-1b-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 280.7 tok/s TG128 @ 1 ctx | 7,507 tok/s PP512 | ||
Qwen3-0.6B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 309.4 tok/s TG128 @ 1 ctx | 49,488 tok/s PP512 | ||
Llama-3.2-1B-Instruct-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 254.6 tok/s TG128 @ 1 ctx | 37,864 tok/s PP512 | ||
gemma-3-1b-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 220.7 tok/s TG128 @ 1 ctx | 3,369 tok/s PP512 | ||
Qwen3-0.6B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 466.7 tok/s TG128 @ 1 ctx | 10,006 tok/s PP512 | ||
gemma-3-1b-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 213.6 tok/s TG128 @ 1 ctx | 4,098 tok/s PP512 | ||
gemma-3-1b-it-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 265.1 tok/s TG128 @ 1 ctx | 33,122 tok/s PP512 | ||
Qwen3-0.6B-cuda-q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 450.2 tok/s TG128 @ 1 ctx | 51,746 tok/s PP512 | ||
gemma-3-1b-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 351.9 tok/s TG128 @ 1 ctx | 7,705 tok/s PP512 | ||
gemma-3-1b-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 288.6 tok/s TG128 @ 1 ctx | 14,025 tok/s PP512 | ||
Qwen3-0.6B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 401.9 tok/s TG128 @ 1 ctx | 5,025 tok/s PP512 | ||
Qwen3-0.6B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 366.4 tok/s TG128 @ 1 ctx | 5,861 tok/s PP512 | ||
Qwen3-0.6B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | unknown | CUDA | 404.0 tok/s TG128 @ 1 ctx | 51,376 tok/s PP512 | ||
Qwen3-0.6B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 573.4 tok/s TG128 @ 1 ctx | 9,924 tok/s PP512 | ||
Qwen3-0.6B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 456.0 tok/s TG128 @ 1 ctx | 21,115 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 94.9 tok/s TG128 @ 1 ctx | 1,638 tok/s PP512 | ||
Qwen3.6-27B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 17.5 tok/s TG128 @ 1 ctx | 222 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 17.7 tok/s TG128 @ 1 ctx | 221 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 104.6 tok/s TG128 @ 1 ctx | 878 tok/s PP512 | ||
Qwen3.8-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 31.5 tok/s TG128 @ 1 ctx | 221 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 95.9 tok/s TG128 @ 1 ctx | 1,795 tok/s PP512 | ||
gpt-oss-120b-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 121.4 tok/s TG128 @ 1 ctx | 1,695 tok/s PP512 | ||
gpt-oss-120b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 129.4 tok/s TG128 @ 1 ctx | 1,646 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 BaseRTbf16 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 71.8 tok/s TG128 @ 1 ctx | 691 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 73.8 tok/s TG128 @ 1 ctx | 1,679 tok/s PP512 | ||
gpt-oss-20b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 185.1 tok/s TG128 @ 1 ctx | 2,554 tok/s PP512 | ||
gpt-oss-20b-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 175.8 tok/s TG128 @ 1 ctx | 2,627 tok/s PP512 | ||
Qwen3.8-27B-Q4-mtp BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 39.5 tok/s TG128 @ 1 ctx | 288 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 171.6 tok/s TG128 @ 1 ctx | 2,295 tok/s PP512 | ||
muse-glimmer-30B-kquant-dynamic BaseRTpassthrough_gguf The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 27.3 tok/s TG128 @ 1 ctx | 399 tok/s PP512 | ||
muse-glimmer-30B-kquant-dynamic BaseRTpassthrough_gguf The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 22.8 tok/s TG128 @ 1 ctx | 254 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 139.7 tok/s TG128 @ 1 ctx | 886 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 140.1 tok/s TG128 @ 1 ctx | 895 tok/s PP512 | ||
muse-glimmer-30B-kquant-17gb BaseRTpassthrough_gguf The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 27.2 tok/s TG128 @ 1 ctx | 266 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 169.1 tok/s TG128 @ 1 ctx | 1,632 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 204.6 tok/s TG128 @ 1 ctx | 2,685 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 193.1 tok/s TG128 @ 1 ctx | 1,828 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 179.1 tok/s TG128 @ 1 ctx | 1,150 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 176.8 tok/s TG128 @ 1 ctx | 1,150 tok/s PP512 | ||
Qwen3.8-27B-Q4-mtp BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M4 Max | Metal | 31.5 tok/s TG128 @ 1 ctx | 221 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 179.3 tok/s TG128 @ 1 ctx | 2,692 tok/s PP512 | ||
Qwen3-1.7B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 125.3 tok/s TG128 @ 1 ctx | 1,822 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 90.3 tok/s TG128 @ 1 ctx | 734 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 113.5 tok/s TG128 @ 1 ctx | 1,138 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 113.9 tok/s TG128 @ 1 ctx | 1,149 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 95.0 tok/s TG128 @ 1 ctx | 943 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 77.9 tok/s TG128 @ 1 ctx | 727 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 78.4 tok/s TG128 @ 1 ctx | 732 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 139.8 tok/s TG128 @ 1 ctx | 1,789 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 126.0 tok/s TG128 @ 1 ctx | 3,722 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 71.2 tok/s TG128 @ 1 ctx | 943 tok/s PP512 | ||
gemma-3-1b-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 328.0 tok/s TG128 @ 1 ctx | 9,903 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 410.1 tok/s TG128 @ 1 ctx | 9,066 tok/s PP512 | ||
gemma-3-1b-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 257.8 tok/s TG128 @ 1 ctx | 9,953 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 306.7 tok/s TG128 @ 1 ctx | 1,759 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 307.4 tok/s TG128 @ 1 ctx | 5,420 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 293.8 tok/s TG128 @ 1 ctx | 1,756 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 345.2 tok/s TG128 @ 1 ctx | 9,055 tok/s PP512 | ||
Qwen3-1.7B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 238.6 tok/s TG128 @ 1 ctx | 5,698 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 165.7 tok/s TG128 @ 1 ctx | 2,461 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 222.9 tok/s TG128 @ 1 ctx | 1,756 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 222.4 tok/s TG128 @ 1 ctx | 1,696 tok/s PP512 | ||
Qwen3-4B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 56.3 tok/s TG128 @ 1 ctx | 726 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 195.4 tok/s TG128 @ 1 ctx | 3,241 tok/s PP512 | ||
gemma-3-1b-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 170.0 tok/s TG128 @ 1 ctx | 4,120 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 153.7 tok/s TG128 @ 1 ctx | 2,529 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 242.1 tok/s TG128 @ 1 ctx | 3,333 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 155.6 tok/s TG128 @ 1 ctx | 2,582 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 219.7 tok/s TG128 @ 1 ctx | 2,244 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 137.4 tok/s TG128 @ 1 ctx | 8,996 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 140.1 tok/s TG128 @ 1 ctx | 1,797 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 192.9 tok/s TG128 @ 1 ctx | 429 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 154.4 tok/s TG128 @ 1 ctx | 3,316 tok/s PP512 | ||
Qwen3-4B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 116.8 tok/s TG128 @ 1 ctx | 2,441 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 118.3 tok/s TG128 @ 1 ctx | 2,557 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 118.2 tok/s TG128 @ 1 ctx | 2,559 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 190.0 tok/s TG128 @ 1 ctx | 439 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 129.3 tok/s TG128 @ 1 ctx | 1,440 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 94.6 tok/s TG128 @ 1 ctx | 3,610 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 113.6 tok/s TG128 @ 1 ctx | 1,357 tok/s PP512 | ||
Qwen3-1.7B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 153.9 tok/s TG128 @ 1 ctx | 2,223 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 229.4 tok/s TG128 @ 1 ctx | 3,372 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 124.4 tok/s TG128 @ 1 ctx | 1,438 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 101.9 tok/s TG128 @ 1 ctx | 927 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 56.2 tok/s TG128 @ 1 ctx | 731 tok/s PP512 | ||
gemma-4-E2B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 116.6 tok/s TG128 @ 1 ctx | 8,610 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 78.9 tok/s TG128 @ 1 ctx | 1,388 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 141.5 tok/s TG128 @ 1 ctx | 400 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 75.3 tok/s TG128 @ 1 ctx | 1,392 tok/s PP512 | ||
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 75.4 tok/s TG128 @ 1 ctx | 3,499 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 140.7 tok/s TG128 @ 1 ctx | 438 tok/s PP512 | ||
Qwen3-8B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 72.5 tok/s TG128 @ 1 ctx | 1,338 tok/s PP512 | ||
gpt-oss-20b-MXFP4 BaseRTmxfp4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 163.9 tok/s TG128 @ 1 ctx | 2,590 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 110.7 tok/s TG128 @ 1 ctx | 1,229 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 36.8 tok/s TG128 @ 1 ctx | 281 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 91.3 tok/s TG128 @ 1 ctx | 922 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 81.5 tok/s TG128 @ 1 ctx | 1,664 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 56.3 tok/s TG128 @ 1 ctx | 731 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 93.2 tok/s TG128 @ 1 ctx | 921 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 81.5 tok/s TG128 @ 1 ctx | 2,422 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 120.8 tok/s TG128 @ 1 ctx | 4,521 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 40.6 tok/s TG128 @ 1 ctx | 509 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 135.3 tok/s TG128 @ 1 ctx | 2,416 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 137.1 tok/s TG128 @ 1 ctx | 2,287 tok/s PP512 | ||
gemma-4-E2B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 91.1 tok/s TG128 @ 1 ctx | 4,442 tok/s PP512 | ||
muse-glimmer-30B-kquant-17gb BaseRTpassthrough_gguf The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 31.1 tok/s TG128 @ 1 ctx | 405 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 63.7 tok/s TG128 @ 1 ctx | 509 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 69.1 tok/s TG128 @ 1 ctx | 1,094 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 71.5 tok/s TG128 @ 1 ctx | 925 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 133.0 tok/s TG128 @ 1 ctx | 947 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 59.0 tok/s TG128 @ 1 ctx | 394 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 133.0 tok/s TG128 @ 1 ctx | 922 tok/s PP512 | ||
Qwen3-4B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 71.3 tok/s TG128 @ 1 ctx | 920 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 75.3 tok/s TG128 @ 1 ctx | 2,258 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 88.4 tok/s TG128 @ 1 ctx | 1,240 tok/s PP512 | ||
gemma-3-1b-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 178.8 tok/s TG128 @ 1 ctx | 3,337 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 72.1 tok/s TG128 @ 1 ctx | 925 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 66.4 tok/s TG128 @ 1 ctx | 511 tok/s PP512 | ||
Qwen3.6-27B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 22.1 tok/s TG128 @ 1 ctx | 280 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 75.9 tok/s TG128 @ 1 ctx | 1,394 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 52.6 tok/s TG128 @ 1 ctx | 394 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 60.2 tok/s TG128 @ 1 ctx | 507 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 22.1 tok/s TG128 @ 1 ctx | 280 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 30.3 tok/s TG128 @ 1 ctx | 221 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 38.6 tok/s TG128 @ 1 ctx | 509 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 95.9 tok/s TG128 @ 1 ctx | 2,289 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 95.8 tok/s TG128 @ 1 ctx | 2,391 tok/s PP512 | ||
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 52.0 tok/s TG128 @ 1 ctx | 1,368 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 102.1 tok/s TG128 @ 1 ctx | 2,311 tok/s PP512 | ||
Qwen3-8B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 38.1 tok/s TG128 @ 1 ctx | 500 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 101.9 tok/s TG128 @ 1 ctx | 2,315 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 56.1 tok/s TG128 @ 1 ctx | 394 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 109.6 tok/s TG128 @ 1 ctx | 927 tok/s PP512 | ||
gpt-oss-20b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 82.3 tok/s TG128 @ 1 ctx | 881 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 109.1 tok/s TG128 @ 1 ctx | 939 tok/s PP512 | ||
gpt-oss-20b-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 76.7 tok/s TG128 @ 1 ctx | 880 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 110.8 tok/s TG128 @ 1 ctx | 910 tok/s PP512 | ||
gpt-oss-20b-MXFP4 BaseRTmxfp4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 76.6 tok/s TG128 @ 1 ctx | 890 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 109.5 tok/s TG128 @ 1 ctx | 913 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 17.9 tok/s TG128 @ 1 ctx | 80 tok/s PP512 | ||
gpt-oss-120b-MXFP4 BaseRTmxfp4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 114.0 tok/s TG128 @ 1 ctx | 1,700 tok/s PP512 | ||
gpt-oss-20b-MXFP4 BaseRTmxfp4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 146.7 tok/s TG128 @ 1 ctx | 1,715 tok/s PP512 | ||
gemma-4-E2B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 83.9 tok/s TG128 @ 1 ctx | 3,628 tok/s PP512 | ||
Qwen3.5-122B-A10B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 66.4 tok/s TG128 @ 1 ctx | 536 tok/s PP512 | ||
Qwen3.5-122B-A10B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M3 Ultra | Metal | 66.3 tok/s TG128 @ 1 ctx | 532 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 51.5 tok/s TG128 @ 1 ctx | 871 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 33.8 tok/s TG128 @ 1 ctx | 393 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 87.2 tok/s TG128 @ 1 ctx | 901 tok/s PP512 | ||
gpt-oss-20b-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 146.9 tok/s TG128 @ 1 ctx | 1,700 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 87.7 tok/s TG128 @ 1 ctx | 901 tok/s PP512 | ||
Qwen3.8-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra | Metal | 38.0 tok/s TG128 @ 1 ctx | 282 tok/s PP512 | ||
Qwen3.8-27B-Q4-mtp BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 18.2 tok/s TG128 @ 1 ctx | 82 tok/s PP512 | ||
gpt-oss-20b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 160.5 tok/s TG128 @ 1 ctx | 1,709 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 32.1 tok/s TG128 @ 1 ctx | 392 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 110.3 tok/s TG128 @ 1 ctx | 870 tok/s PP512 | ||
muse-glimmer-30B-kquant-17gb BaseRTpassthrough_gguf The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 17.3 tok/s TG128 @ 1 ctx | 140 tok/s PP512 | ||
Qwen3-8B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 59.6 tok/s TG128 @ 1 ctx | 942 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 93.7 tok/s TG128 @ 1 ctx | 280 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 94.2 tok/s TG128 @ 1 ctx | 278 tok/s PP512 | ||
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 44.5 tok/s TG128 @ 1 ctx | 1,081 tok/s PP512 | ||
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 77.4 tok/s TG128 @ 1 ctx | 2,481 tok/s PP512 | ||
muse-glimmer-30B-kquant-dynamic BaseRTpassthrough_gguf The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 14.3 tok/s TG128 @ 1 ctx | 136 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 60.8 tok/s TG128 @ 1 ctx | 947 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 45.5 tok/s TG128 @ 1 ctx | 877 tok/s PP512 | ||
Qwen3.6-27B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 11.0 tok/s TG128 @ 1 ctx | 83 tok/s PP512 | ||
Qwen3-8B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 31.6 tok/s TG128 @ 1 ctx | 392 tok/s PP512 | ||
Qwen3.5-122B-A10B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 30.6 tok/s TG128 @ 1 ctx | 799 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 64.1 tok/s TG128 @ 1 ctx | 946 tok/s PP512 | ||
gpt-oss-120b-MXFP4 BaseRTmxfp4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 41.4 tok/s TG128 @ 1 ctx | 2,622 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 11.0 tok/s TG128 @ 1 ctx | 82 tok/s PP512 | ||
gemma-4-E2B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 132.2 tok/s TG128 @ 1 ctx | 7,448 tok/s PP512 | ||
Qwen3.5-122B-A10B-Q4 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 31.2 tok/s TG128 @ 1 ctx | 795 tok/s PP512 | ||
gpt-oss-120b-MXFP4 BaseRTmxfp4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 41.7 tok/s TG128 @ 1 ctx | 2,626 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 105.5 tok/s TG128 @ 1 ctx | 946 tok/s PP512 | ||
gpt-oss-120b-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 35.8 tok/s TG128 @ 1 ctx | 2,638 tok/s PP512 | ||
gpt-oss-20b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 79.3 tok/s TG128 @ 1 ctx | 732 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 99.2 tok/s TG128 @ 1 ctx | 943 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 11.0 tok/s TG128 @ 1 ctx | 82 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 109.3 tok/s TG128 @ 1 ctx | 2,552 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 110.3 tok/s TG128 @ 1 ctx | 947 tok/s PP512 | ||
gpt-oss-120b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 39.7 tok/s TG128 @ 1 ctx | 2,619 tok/s PP512 | ||
gpt-oss-120b-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 35.5 tok/s TG128 @ 1 ctx | 2,278 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 104.3 tok/s TG128 @ 1 ctx | 1,714 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 64.6 tok/s TG128 @ 1 ctx | 893 tok/s PP512 | ||
gpt-oss-20b-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 73.7 tok/s TG128 @ 1 ctx | 731 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 63.7 tok/s TG128 @ 1 ctx | 895 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 104.3 tok/s TG128 @ 1 ctx | 1,723 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 61.1 tok/s TG128 @ 1 ctx | 857 tok/s PP512 | ||
Qwen3.6-35B-A3B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 55.4 tok/s TG128 @ 1 ctx | 2,181 tok/s PP512 | ||
Qwen3.5-35B-A3B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 54.7 tok/s TG128 @ 1 ctx | 2,447 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 60.6 tok/s TG128 @ 1 ctx | 858 tok/s PP512 | ||
Qwen3-4B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 105.4 tok/s TG128 @ 1 ctx | 1,712 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 72.0 tok/s TG128 @ 1 ctx | 250 tok/s PP512 | ||
Qwen3.6-35B-A3B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 54.4 tok/s TG128 @ 1 ctx | 2,188 tok/s PP512 | ||
Qwen3.5-35B-A3B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 54.2 tok/s TG128 @ 1 ctx | 2,428 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 133.1 tok/s TG128 @ 1 ctx | 2,218 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 61.2 tok/s TG128 @ 1 ctx | 7,253 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 175.3 tok/s TG128 @ 1 ctx | 7,670 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q8 BaseRTQ8 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | Apple M1 Max | Metal | 72.2 tok/s TG128 @ 1 ctx | 251 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 7.5 tok/s TG128 @ 1 ctx | 1,127 tok/s PP512 | ||
Qwen3.6-27B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 8.4 tok/s TG128 @ 1 ctx | 1,146 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 49.4 tok/s TG128 @ 1 ctx | 7,315 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 122.7 tok/s TG128 @ 1 ctx | 1,721 tok/s PP512 | ||
Qwen3.8-27B-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 7.6 tok/s TG128 @ 1 ctx | 1,152 tok/s PP512 | ||
Qwen3.6-27B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 7.5 tok/s TG128 @ 1 ctx | 1,141 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 121.9 tok/s TG128 @ 1 ctx | 1,711 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 70.8 tok/s TG128 @ 1 ctx | 247 tok/s PP512 | ||
gpt-oss-20b-MXFP4 BaseRTmxfp4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro | Metal | 72.7 tok/s TG128 @ 1 ctx | 734 tok/s PP512 | ||
gemma-4-26B-A4B-it-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 40.4 tok/s TG128 @ 1 ctx | 6,045 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 178.8 tok/s TG128 @ 1 ctx | 2,202 tok/s PP512 | ||
Qwen3.6-35B-A3B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 72.8 tok/s TG128 @ 1 ctx | 2,279 tok/s PP512 | ||
Qwen3.5-2B-Base-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 208.0 tok/s TG128 @ 1 ctx | 1,727 tok/s PP512 | ||
Qwen3.5-35B-A3B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 92.4 tok/s TG128 @ 1 ctx | 2,521 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 72.2 tok/s TG128 @ 1 ctx | 232 tok/s PP512 | ||
Qwen3.6-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 84.3 tok/s TG128 @ 1 ctx | 2,028 tok/s PP512 | ||
Qwen3.6-27B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 12.3 tok/s TG128 @ 1 ctx | 1,127 tok/s PP512 | ||
Qwen3.5-35B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 84.4 tok/s TG128 @ 1 ctx | 2,093 tok/s PP512 | ||
Qwen3.5-2B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 205.4 tok/s TG128 @ 1 ctx | 1,721 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 99.0 tok/s TG128 @ 1 ctx | 7,439 tok/s PP512 | ||
NVIDIA-Nemotron-3-Nano-30B-A3B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 99.8 tok/s TG128 @ 1 ctx | 3,862 tok/s PP512 | ||
Qwen3.8-27B-Q4-mtp BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 13.1 tok/s TG128 @ 1 ctx | 1,136 tok/s PP512 | ||
Qwen3.8-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 13.1 tok/s TG128 @ 1 ctx | 1,131 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 157.5 tok/s TG128 @ 1 ctx | 1,725 tok/s PP512 | ||
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 80.7 tok/s TG128 @ 1 ctx | 4,715 tok/s PP512 | ||
Qwen3.6-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 13.0 tok/s TG128 @ 1 ctx | 344 tok/s PP512 | ||
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 81.1 tok/s TG128 @ 1 ctx | 4,738 tok/s PP512 | ||
Qwen3.8-27B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max | Metal | 18.2 tok/s TG128 @ 1 ctx | 82 tok/s PP512 | ||
Qwen3-1.7B-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 224.1 tok/s TG128 @ 1 ctx | 4,025 tok/s PP512 | ||
gemma-4-26B-A4B-it-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 45.3 tok/s TG128 @ 1 ctx | 6,190 tok/s PP512 | ||
gemma-4-26B-A4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 44.0 tok/s TG128 @ 1 ctx | 6,179 tok/s PP512 | ||
gpt-oss-20b-MXFP4 BaseRTmxfp4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 60.2 tok/s TG128 @ 1 ctx | 4,424 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 320.5 tok/s TG128 @ 1 ctx | 6,058 tok/s PP512 | ||
gpt-oss-20b-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 51.4 tok/s TG128 @ 1 ctx | 4,421 tok/s PP512 | ||
gpt-oss-20b-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 57.3 tok/s TG128 @ 1 ctx | 4,292 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 295.1 tok/s TG128 @ 1 ctx | 1,713 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 25.4 tok/s TG128 @ 1 ctx | 7,299 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 27.0 tok/s TG128 @ 1 ctx | 7,510 tok/s PP512 | ||
gemma-4-E2B-it-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 87.7 tok/s TG128 @ 1 ctx | 19,246 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 301.7 tok/s TG128 @ 1 ctx | 1,718 tok/s PP512 | ||
Llama-3.1-8B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 53.1 tok/s TG128 @ 1 ctx | 7,567 tok/s PP512 | ||
Qwen3-8B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 50.3 tok/s TG128 @ 1 ctx | 1,452 tok/s PP512 | ||
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 71.3 tok/s TG128 @ 1 ctx | 3,674 tok/s PP512 | ||
Mistral-7B-Instruct-v0.3-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 53.5 tok/s TG128 @ 1 ctx | 7,554 tok/s PP512 | ||
gemma-4-E2B-it-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 79.0 tok/s TG128 @ 1 ctx | 18,372 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 318.4 tok/s TG128 @ 1 ctx | 4,146 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 54.8 tok/s TG128 @ 1 ctx | 10,970 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 54.7 tok/s TG128 @ 1 ctx | 11,473 tok/s PP512 | ||
Llama-3.2-3B-Instruct-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 69.4 tok/s TG128 @ 1 ctx | 14,988 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 68.7 tok/s TG128 @ 1 ctx | 14,871 tok/s PP512 | ||
gemma-4-E2B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 139.8 tok/s TG128 @ 1 ctx | 12,036 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 371.7 tok/s TG128 @ 1 ctx | 5,963 tok/s PP512 | ||
Qwen3-4B-Thinking-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 73.2 tok/s TG128 @ 1 ctx | 11,020 tok/s PP512 | ||
Qwen3-4B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 73.7 tok/s TG128 @ 1 ctx | 11,246 tok/s PP512 | ||
Llama-3.2-3B-Instruct-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 89.7 tok/s TG128 @ 1 ctx | 14,073 tok/s PP512 | ||
Qwen3-4B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 91.3 tok/s TG128 @ 1 ctx | 2,822 tok/s PP512 | ||
Qwen3.5-2B-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 113.5 tok/s TG128 @ 1 ctx | 6,754 tok/s PP512 | ||
gemma-3-1b-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max | Metal | 281.0 tok/s TG128 @ 1 ctx | 7,527 tok/s PP512 | ||
Llama-3.2-3B-Instruct-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 110.5 tok/s TG128 @ 1 ctx | 14,651 tok/s PP512 | ||
Qwen3.5-2B-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 151.5 tok/s TG128 @ 1 ctx | 6,837 tok/s PP512 | ||
Llama-3.2-1B-Instruct-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled. | NVIDIA GB10 | CUDA | 173.7 tok/s TG128 @ 1 ctx | 34,296 tok/s PP512 | ||
Llama-3.2-1B-Instruct-Q8 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 172.8 tok/s TG128 @ 1 ctx | 35,941 tok/s PP512 | ||
Qwen3.5-2B-Base-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 181.9 tok/s TG128 @ 1 ctx | 4,191 tok/s PP512 | ||
Qwen3.5-2B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 181.6 tok/s TG128 @ 1 ctx | 4,185 tok/s PP512 | ||
Qwen3-1.7B-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 | CUDA | 202.5 tok/s TG128 @ 1 ctx | 7,394 tok/s PP512 |