Chips
Loading community benchmarks…
Loading community benchmarks…
Submitted benchmarks for NVIDIA GB10. 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.
NVIDIA GB10 CUDA |
33.2 tok/s TG128 @ 1 ctx |
1,085 tok/s PP512 |
| 41,629.0 MiB |
basecompute |
| View Benchmark |
gpt-oss-120b-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. | NVIDIA GB10 CUDA | 35.5 tok/s TG128 @ 1 ctx | 2,623 tok/s PP512 | 40,828.4 MiB | basecompute | View Benchmark |
Qwen3.5-35B-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. | NVIDIA GB10 CUDA | 54.3 tok/s TG128 @ 1 ctx | 3,647 tok/s PP512 | 22,203.8 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. | NVIDIA GB10 CUDA | 7.5 tok/s TG128 @ 1 ctx | 1,701 tok/s PP512 | 28,071.2 MiB | basecompute | View Benchmark |
gemma-4-26B-A4B-it-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. | NVIDIA GB10 CUDA | 40.5 tok/s TG128 @ 1 ctx | 6,005 tok/s PP512 | 10,543.4 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. | NVIDIA GB10 CUDA | 73.3 tok/s TG128 @ 1 ctx | 3,884 tok/s PP512 | 14,948.7 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. | NVIDIA GB10 CUDA | 86.3 tok/s TG128 @ 1 ctx | 2,899 tok/s PP512 | 16,702.3 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. | NVIDIA GB10 CUDA | 90.6 tok/s TG128 @ 1 ctx | 2,898 tok/s PP512 | 20,118.7 MiB | basecompute | View Benchmark |
Qwen3-30B-A3B-Instruct-2507-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. | NVIDIA GB10 CUDA | 99.1 tok/s TG128 @ 1 ctx | 7,437 tok/s PP512 | 17,902.1 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. | NVIDIA GB10 CUDA | 13.1 tok/s TG128 @ 1 ctx | 1,713 tok/s PP512 | 17,659.4 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. | NVIDIA GB10 CUDA | 80.8 tok/s TG128 @ 1 ctx | 4,718 tok/s PP512 | 13,396.9 MiB | basecompute | View Benchmark |
gemma-4-26B-A4B-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. | NVIDIA GB10 CUDA | 44.1 tok/s TG128 @ 1 ctx | 6,188 tok/s PP512 | 7,350.5 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. | NVIDIA GB10 CUDA | 44.0 tok/s TG128 @ 1 ctx | 6,112 tok/s PP512 | 7,344.0 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. | NVIDIA GB10 CUDA | 59.9 tok/s TG128 @ 1 ctx | 4,448 tok/s PP512 | 16,111.5 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. | NVIDIA GB10 CUDA | 51.5 tok/s TG128 @ 1 ctx | 4,412 tok/s PP512 | 15,013.4 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. | NVIDIA GB10 CUDA | 25.5 tok/s TG128 @ 1 ctx | 7,170 tok/s PP512 | 8,428.8 MiB | basecompute | View Benchmark |
gemma-4-E2B-it-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. | NVIDIA GB10 CUDA | 86.9 tok/s TG128 @ 1 ctx | 19,183 tok/s PP512 | 6,276.6 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. | NVIDIA GB10 CUDA | 51.6 tok/s TG128 @ 1 ctx | 7,333 tok/s PP512 | 5,688.0 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. | NVIDIA GB10 CUDA | 71.8 tok/s TG128 @ 1 ctx | 3,593 tok/s PP512 | 5,672.6 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. | NVIDIA GB10 CUDA | 54.0 tok/s TG128 @ 1 ctx | 7,566 tok/s PP512 | 4,650.5 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. | NVIDIA GB10 CUDA | 54.9 tok/s TG128 @ 1 ctx | 11,378 tok/s PP512 | 4,554.5 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. | NVIDIA GB10 CUDA | 68.2 tok/s TG128 @ 1 ctx | 14,830 tok/s PP512 | 3,785.7 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. | NVIDIA GB10 CUDA | 72.8 tok/s TG128 @ 1 ctx | 10,965 tok/s PP512 | 3,383.2 MiB | basecompute | View Benchmark |
Llama-3.2-3B-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. | NVIDIA GB10 CUDA | 87.8 tok/s TG128 @ 1 ctx | 14,593 tok/s PP512 | 2,889.0 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. | NVIDIA GB10 CUDA | 89.4 tok/s TG128 @ 1 ctx | 2,842 tok/s PP512 | 2,876.0 MiB | basecompute | View Benchmark |