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 |
74.8 tok/s TG128 @ 1 ctx |
4,356 tok/s PP512 |
| 15,633.9 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. | unknown CUDA | 30.2 tok/s TG128 @ 1 ctx | 7,662 tok/s PP512 | 7,739.4 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. | unknown CUDA | 49.7 tok/s TG128 @ 1 ctx | 1,467 tok/s PP512 | 5,111.7 MiB | basecompute | View Benchmark |
gemma-4-E2B-it-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 | 76.0 tok/s TG128 @ 1 ctx | 17,897 tok/s PP512 | 5,289.6 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. | unknown CUDA | 53.3 tok/s TG128 @ 1 ctx | 11,490 tok/s PP512 | 4,649.8 MiB | basecompute | View Benchmark |
Llama-3.2-3B-Instruct-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 | 67.1 tok/s TG128 @ 1 ctx | 15,528 tok/s PP512 | 3,790.8 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. | unknown CUDA | 131.9 tok/s TG128 @ 1 ctx | 11,398 tok/s PP512 | 3,981.7 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. | unknown CUDA | 72.2 tok/s TG128 @ 1 ctx | 11,179 tok/s PP512 | 3,384.9 MiB | basecompute | View Benchmark |
Qwen3.5-2B-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 | 109.1 tok/s TG128 @ 1 ctx | 17,984 tok/s PP512 | 2,941.0 MiB | basecompute | View Benchmark |
Llama-3.2-3B-Instruct-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 | 107.0 tok/s TG128 @ 1 ctx | 15,281 tok/s PP512 | 2,448.7 MiB | basecompute | View Benchmark |
Llama-3.2-1B-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. | unknown CUDA | 168.2 tok/s TG128 @ 1 ctx | 37,392 tok/s PP512 | 1,746.1 MiB | basecompute | View Benchmark |
Qwen3.5-2B-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 | 179.0 tok/s TG128 @ 1 ctx | 6,868 tok/s PP512 | 1,971.0 MiB | basecompute | View Benchmark |
Llama-3.2-1B-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. | unknown CUDA | 191.9 tok/s TG128 @ 1 ctx | 34,471 tok/s PP512 | 1,553.7 MiB | basecompute | View Benchmark |
Llama-3.2-1B-Instruct-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 | 254.6 tok/s TG128 @ 1 ctx | 37,864 tok/s PP512 | 1,256.4 MiB | basecompute | View Benchmark |
Qwen3-0.6B-cuda-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 | 450.2 tok/s TG128 @ 1 ctx | 51,746 tok/s PP512 | 1,242.5 MiB | basecompute | View Benchmark |
Qwen3-0.6B-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 | 404.0 tok/s TG128 @ 1 ctx | 51,376 tok/s PP512 | 1,135.7 MiB | basecompute | View Benchmark |