⚡
Performance benchmark
How fast is the model?
Raw throughput on real hardware – how many tokens a model generates per second, how quickly it processes the prompt and how short the time to first token is. Higher is better.
⚡ Generation (tok/s)🔄 Prefill⏱️ TTFT👥 Concurrency
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.443,88 tok/s TG Prefill 35.348 · TTFT 560 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 2 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.070,56 tok/s TG Prefill 33.741 · TTFT 976 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 3 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.028,53 tok/s TG Prefill 36.884 · TTFT 916 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 4 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.015,69 tok/s TG Prefill 20.061 · TTFT 1.289 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 5 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 961,53 tok/s TG Prefill 32.305 · TTFT 1.633 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 6 | Qwen3-Omni-30B-A3B-ThinkingQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 910,74 tok/s TG Prefill 33.907 · TTFT 1.527 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 7 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 906,04 tok/s TG Prefill 39.029 · TTFT 1.193 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 8 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 842,94 tok/s TG Prefill 31.098 · TTFT 319 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 9 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 726,94 tok/s TG Prefill 10.204 · TTFT 2.619 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 10 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 725,58 tok/s TG Prefill 11.872 · TTFT 2.430 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 11 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 676,76 tok/s TG Prefill 21.675 · TTFT 725 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 12 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 666,52 tok/s TG Prefill 27.804 · TTFT 465 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 13 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 649,04 tok/s TG Prefill 17.868 · TTFT 764 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 14 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 625,71 tok/s TG Prefill 31.724 · TTFT 396 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 15 | Qwen3-Omni-30B-A3B-ThinkingQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 618,22 tok/s TG Prefill 28.790 · TTFT 435 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 16 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 615,82 tok/s TG Prefill 13.999 · TTFT 797 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 17 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 423,35 tok/s TG Prefill 6.026 · TTFT 2.001 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 18 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 411,83 tok/s TG Prefill 7.172 · TTFT 1.728 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 19 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 268,71 tok/s TG Prefill 17.371 · TTFT 114 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 20 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 237,20 tok/s TG Prefill 8.070 · TTFT 353 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 21 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 233,88 tok/s TG Prefill 10.557 · TTFT 236 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 22 | Qwen3-Omni-30B-A3B-ThinkingQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 228,95 tok/s TG Prefill 9.070 · TTFT 302 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 23 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 227,91 tok/s TG Prefill 2.384 · TTFT 1.021 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 24 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,94 tok/s TG Prefill 4.657 · TTFT 527 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 25 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 144,83 tok/s TG Prefill 9.895 · TTFT 217 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 26 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 96,87 tok/s TG Prefill 5.696 · TTFT 375 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 27 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 96,03 tok/s TG Prefill 5.629 · TTFT 380 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 28 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,25 tok/s TG Prefill 12.250 · TTFT 2.840 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 29 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,99 tok/s TG Prefill 8.091 · TTFT 1.621 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 30 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,99 tok/s TG Prefill 4.687 · TTFT 495 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation Edition32x AMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → |
