Chips
Loading community benchmarks…
Loading community benchmarks…
Submitted benchmarks for Apple M3 Ultra. Browse individual runs and their measurement settings, or open the report JSON for full benchmark details.
Peak throughput is the highest reported value and may come from different runs. Compare model, quantisation, backend, and token counts before drawing conclusions. Model verification identifies published artifact bytes; community benchmark execution is not remotely attested.
Apple M3 Ultra Metal |
501.7 tok/s TG128 @ 1 ctx |
12,830 tok/s PP512 |
| 1,368.9 MiB |
basecompute |
| View Benchmark |
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 | 440.2 tok/s TG128 @ 1 ctx | 12,494 tok/s PP512 | 1,641.7 MiB | basecompute | View Benchmark |
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 | 22,666.1 MiB | basecompute | View Benchmark |
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 | 5,597.1 MiB | basecompute | View Benchmark |
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 | 5,596.6 MiB | basecompute | View Benchmark |
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 | 12,584.4 MiB | basecompute | View Benchmark |
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 | 3,677.9 MiB | basecompute | View Benchmark |
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 | 3,678.1 MiB | basecompute | View Benchmark |
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 | 3,678.2 MiB | basecompute | View Benchmark |
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 | 3,677.5 MiB | basecompute | View Benchmark |
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 | 1,105.2 MiB | basecompute | View Benchmark |
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 | 1,106.3 MiB | basecompute | View Benchmark |
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 | 1,913.9 MiB | basecompute | View Benchmark |
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 | 1,913.6 MiB | basecompute | View Benchmark |
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 | 37,635.2 MiB | basecompute | View Benchmark |
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 | 37,631.9 MiB | basecompute | View Benchmark |
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 | 3,951.9 MiB | basecompute | View Benchmark |
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 | 2,747.0 MiB | basecompute | View Benchmark |
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 | 2,746.4 MiB | basecompute | View Benchmark |
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 | 606.9 MiB | basecompute | View Benchmark |
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 | 1,466.5 MiB | basecompute | View Benchmark |
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 | 1,458.9 MiB | basecompute | View Benchmark |
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 | 3,449.5 MiB | basecompute | View Benchmark |
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 | 22,664.1 MiB | basecompute | View Benchmark |
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 | 10,481.7 MiB | basecompute | View Benchmark |