Chips
Loading community benchmarks…
Loading community benchmarks…
Submitted benchmarks for Apple M4 Max. 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 M4 Max Metal |
60.3 tok/s TG128 @ 1 ctx |
948 tok/s PP512 |
| 10,328.8 MiB |
basecompute |
| View Benchmark |
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 | 10,274.4 MiB | basecompute | View Benchmark |
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 | 6,185.2 MiB | basecompute | View Benchmark |
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 | 6,131.3 MiB | basecompute | View Benchmark |
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 | 6,045.4 MiB | basecompute | View Benchmark |
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 | 6,045.9 MiB | basecompute | View Benchmark |
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 | 4,779.3 MiB | basecompute | View Benchmark |
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 | 2,963.1 MiB | basecompute | View Benchmark |
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 | 2,962.4 MiB | basecompute | View Benchmark |
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 | 3,906.7 MiB | basecompute | View Benchmark |
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 | 3,906.8 MiB | basecompute | View Benchmark |
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 | 2,077.5 MiB | basecompute | View Benchmark |
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 | 2,078.2 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 M4 Max Metal | 73.9 tok/s TG128 @ 1 ctx | 1,677 tok/s PP512 | 3,963.8 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 M4 Max Metal | 142.2 tok/s TG128 @ 1 ctx | 1,790 tok/s PP512 | 1,470.6 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 M4 Max Metal | 80.3 tok/s TG128 @ 1 ctx | 1,669 tok/s PP512 | 3,459.6 MiB | basecompute | View Benchmark |
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 | 10,374.1 MiB | basecompute | View Benchmark |
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 | 6,267.7 MiB | basecompute | View Benchmark |
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 | 5,534.9 MiB | basecompute | View Benchmark |
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 | 2,620.3 MiB | basecompute | View Benchmark |
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 | 3,335.4 MiB | basecompute | View Benchmark |
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 | 6,045.2 MiB | basecompute | View Benchmark |
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 | 1,596.2 MiB | basecompute | View Benchmark |
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 | 3,906.8 MiB | basecompute | View Benchmark |
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 | 2,948.3 MiB | basecompute | View Benchmark |