Chips
Loading community benchmarks…
Loading community benchmarks…
Submitted benchmarks for Apple M4 Pro. 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 Pro Metal |
173.9 tok/s TG128 @ 1 ctx |
1,810 tok/s PP512 |
| 2,083.5 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 Pro Metal | 112.7 tok/s TG128 @ 1 ctx | 1,793 tok/s PP512 | 2,968.4 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 Pro Metal | 113.4 tok/s TG128 @ 1 ctx | 1,812 tok/s PP512 | 2,968.2 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 Pro Metal | 172.3 tok/s TG128 @ 1 ctx | 1,835 tok/s PP512 | 2,083.4 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 M4 Pro Metal | 72.3 tok/s TG128 @ 1 ctx | 737 tok/s PP512 | 10,113.8 MiB | basecompute | View Benchmark |
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 | 8,245.3 MiB | basecompute | View Benchmark |
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 | 7,893.5 MiB | basecompute | View Benchmark |
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 | 10,334.5 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 Pro Metal | 33.6 tok/s TG128 @ 1 ctx | 391 tok/s PP512 | 10,275.7 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 Pro Metal | 56.1 tok/s TG128 @ 1 ctx | 727 tok/s PP512 | 6,047.5 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 Pro Metal | 56.0 tok/s TG128 @ 1 ctx | 726 tok/s PP512 | 6,047.6 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 Pro Metal | 77.8 tok/s TG128 @ 1 ctx | 727 tok/s PP512 | 3,909.0 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 Pro Metal | 77.8 tok/s TG128 @ 1 ctx | 725 tok/s PP512 | 3,908.8 MiB | basecompute | View Benchmark |
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 | 2,968.1 MiB | basecompute | View Benchmark |
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 | 2,968.3 MiB | basecompute | View Benchmark |
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 | 2,083.3 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 Pro Metal | 31.5 tok/s TG128 @ 1 ctx | 393 tok/s PP512 | 10,375.6 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 Pro Metal | 44.1 tok/s TG128 @ 1 ctx | 1,072 tok/s PP512 | 5,540.0 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 Pro Metal | 83.8 tok/s TG128 @ 1 ctx | 3,633 tok/s PP512 | 2,625.5 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 Pro Metal | 55.7 tok/s TG128 @ 1 ctx | 394 tok/s PP512 | 6,190.6 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 Pro Metal | 52.4 tok/s TG128 @ 1 ctx | 399 tok/s PP512 | 6,270.1 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 Pro Metal | 68.8 tok/s TG128 @ 1 ctx | 1,101 tok/s PP512 | 3,340.7 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 Pro Metal | 58.5 tok/s TG128 @ 1 ctx | 392 tok/s PP512 | 6,132.1 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 Pro Metal | 55.8 tok/s TG128 @ 1 ctx | 725 tok/s PP512 | 6,047.5 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 Pro Metal | 70.7 tok/s TG128 @ 1 ctx | 934 tok/s PP512 | 4,785.0 MiB | basecompute | View Benchmark |