Chips
Loading community benchmarks…
Loading community benchmarks…
Submitted benchmarks for unknown. 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.
unknown CUDA |
54.7 tok/s TG128 @ 1 ctx |
3,156 tok/s PP512 |
| 30,038.4 MiB |
basecompute |
| View Benchmark |
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 | 22,887.4 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. | unknown CUDA | 8.3 tok/s TG128 @ 1 ctx | 1,722 tok/s PP512 | 28,299.4 MiB | basecompute | View Benchmark |
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 | 28,184.2 MiB | basecompute | View Benchmark |
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 | 15,525.5 MiB | basecompute | View Benchmark |
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 | 14,579.8 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. | unknown CUDA | 104.8 tok/s TG128 @ 1 ctx | 2,765 tok/s PP512 | 20,472.7 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. | unknown CUDA | 104.8 tok/s TG128 @ 1 ctx | 2,937 tok/s PP512 | 20,475.4 MiB | basecompute | View Benchmark |
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 | 18,320.0 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. | unknown CUDA | 13.1 tok/s TG128 @ 1 ctx | 849 tok/s PP512 | 17,760.8 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. | unknown CUDA | 13.1 tok/s TG128 @ 1 ctx | 395 tok/s PP512 | 15,908.4 MiB | basecompute | View Benchmark |
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 | 3,441.5 MiB | basecompute | View Benchmark |
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 | 2,658.6 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. | unknown CUDA | 182.5 tok/s TG128 @ 1 ctx | 6,875 tok/s PP512 | 2,244.2 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. | unknown CUDA | 183.2 tok/s TG128 @ 1 ctx | 6,988 tok/s PP512 | 2,244.4 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. | unknown CUDA | 42.2 tok/s TG128 @ 1 ctx | 2,631 tok/s PP512 | 42,350.7 MiB | basecompute | View Benchmark |
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 | 34,204.0 MiB | basecompute | View Benchmark |
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 | 29,043.1 MiB | basecompute | View Benchmark |
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 | 21,306.9 MiB | basecompute | View Benchmark |
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 | 28,070.2 MiB | basecompute | View Benchmark |
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 | 21,430.4 MiB | basecompute | View Benchmark |
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 | 18,318.9 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. | unknown CUDA | 77.7 tok/s TG128 @ 1 ctx | 3,911 tok/s PP512 | 7,141.2 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. | unknown CUDA | 103.7 tok/s TG128 @ 1 ctx | 4,780 tok/s PP512 | 17,305.7 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. | unknown CUDA | 14.1 tok/s TG128 @ 1 ctx | 385 tok/s PP512 | 16,138.1 MiB | basecompute | View Benchmark |