Chips
Loading community benchmarks…
Loading community benchmarks…
Submitted benchmarks for Apple M1 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 M1 Max Metal |
188.3 tok/s TG128 @ 1 ctx |
2,109 tok/s PP512 |
| 2,083.8 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 M1 Max Metal | 138.5 tok/s TG128 @ 1 ctx | 2,059 tok/s PP512 | 2,969.6 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 M1 Max Metal | 138.3 tok/s TG128 @ 1 ctx | 2,079 tok/s PP512 | 2,969.1 MiB | basecompute | View Benchmark |
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 | 22,685.5 MiB | basecompute | View Benchmark |
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 | 22,796.4 MiB | basecompute | View Benchmark |
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 | 2,875.1 MiB | basecompute | View Benchmark |
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 | 2,875.2 MiB | basecompute | View Benchmark |
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 | 37,652.7 MiB | basecompute | View Benchmark |
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 | 37,762.6 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 M1 Max Metal | 71.8 tok/s TG128 @ 1 ctx | 871 tok/s PP512 | 57,158.2 MiB | basecompute | View Benchmark |
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 | 56,932.8 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 M1 Max Metal | 188.6 tok/s TG128 @ 1 ctx | 2,105 tok/s PP512 | 2,084.6 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 M1 Max Metal | 71.6 tok/s TG128 @ 1 ctx | 828 tok/s PP512 | 58,084.3 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 M1 Max Metal | 71.7 tok/s TG128 @ 1 ctx | 877 tok/s PP512 | 57,853.8 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 M1 Max Metal | 60.6 tok/s TG128 @ 1 ctx | 856 tok/s PP512 | 1,122.9 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 M1 Max Metal | 64.5 tok/s TG128 @ 1 ctx | 893 tok/s PP512 | 1,932.9 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 M1 Max Metal | 11.0 tok/s TG128 @ 1 ctx | 143 tok/s PP512 | 37,652.6 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 M1 Max Metal | 11.0 tok/s TG128 @ 1 ctx | 142 tok/s PP512 | 37,653.0 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 M1 Max Metal | 44.5 tok/s TG128 @ 1 ctx | 876 tok/s PP512 | 3,969.6 MiB | basecompute | View Benchmark |
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 | 623.0 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 M1 Max Metal | 91.5 tok/s TG128 @ 1 ctx | 858 tok/s PP512 | 2,767.1 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 M1 Max Metal | 92.6 tok/s TG128 @ 1 ctx | 880 tok/s PP512 | 2,766.7 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 M1 Max Metal | 17.3 tok/s TG128 @ 1 ctx | 140 tok/s PP512 | 623.3 MiB | basecompute | View Benchmark |
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 | 1,123.3 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 M1 Max Metal | 18.1 tok/s TG128 @ 1 ctx | 143 tok/s PP512 | 22,686.1 MiB | basecompute | View Benchmark |