⚡
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 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 259,86 tok/s TG Prefill 9.253 · TTFT 3.361 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 226,59 tok/s TG Prefill 9.526 · TTFT 3.488 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 225,82 tok/s TG Prefill 9.739 · TTFT 3.277 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 4 | Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 215,97 tok/s TG Prefill 9.775 · TTFT 3.283 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 5 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 187,50 tok/s TG Prefill 6.698 · TTFT 2.090 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 173,08 tok/s TG Prefill 7.158 · TTFT 2.024 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 7 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,96 tok/s TG Prefill 3.010 · TTFT 18.082 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | vLLMgodclawAWQ | Details → | |
| 8 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,19 tok/s TG Prefill 7.879 · TTFT 1.850 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 9 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 160,26 tok/s TG Prefill 4.979 · TTFT 6.510 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 10 | Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 158,90 tok/s TG Prefill 7.616 · TTFT 1.908 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 11 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 122,88 tok/s TG Prefill 2.387 · TTFT 7.059 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | vLLMgodclawAWQ | Details → | |
| 12 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,79 tok/s TG Prefill 3.816 · TTFT 3.796 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 13 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,40 tok/s TG Prefill 3.776 · TTFT 651 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 14 | Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 100,62 tok/s TG Prefill 3.646 · TTFT 677 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 15 | Qwen2.5-3B-Instruct3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,93 tok/s TG Prefill 4.119 · TTFT 596 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 16 | Llama-3.2-3B-Instruct3BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,69 tok/s TG Prefill 3.840 · TTFT 645 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 17 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 61,51 tok/s TG Prefill 1.097 · TTFT 2.256 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | vLLMgodclawAWQ | Details → | |
| 18 | Qwen2.5-7B-Instruct7BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 56,92 tok/s TG Prefill 2.151 · TTFT 1.142 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,70 tok/s TG Prefill 3.624 · TTFT 5.459 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 20 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,91 tok/s TG Prefill 3.620 · TTFT 2.732 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 21 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,14 tok/s TG Prefill 2.500 · TTFT 791 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 22 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,51 tok/s TG Prefill 79 · TTFT 326.271 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 23 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,06 tok/s TG Prefill 56 · TTFT 178.109 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 24 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,35 tok/s TG Prefill 51 · TTFT 38.075 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 25 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,11 tok/s TG Prefill 29 · TTFT 379.775 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 14,47 tok/s TG Prefill 97 · TTFT 222.547 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 13,88 tok/s TG Prefill 24 · TTFT 89.272 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,77 tok/s TG Prefill 89 · TTFT 119.492 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,52 tok/s TG Prefill 71 · TTFT 152.830 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,97 tok/s TG Prefill 72 · TTFT 153.653 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,14 tok/s TG Prefill 69 · TTFT 35.318 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | Qwen3.5-122B-A10B122BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,07 tok/s TG Prefill 8 · TTFT 236.831 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,79 tok/s TG Prefill 16 · TTFT 131.537 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,74 tok/s TG Prefill 74 · TTFT 32.942 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,64 tok/s TG Prefill 73 · TTFT 33.548 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,60 tok/s TG Prefill 73 · TTFT 150.849 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,46 tok/s TG Prefill 79 · TTFT 25.000 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,09 tok/s TG Prefill 100 · TTFT 121.223 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,05 tok/s TG Prefill 104 · TTFT 116.729 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,88 tok/s TG Prefill 61 · TTFT 35.422 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,86 tok/s TG Prefill 61 · TTFT 35.481 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,33 tok/s TG Prefill 74 · TTFT 150.609 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,29 tok/s TG Prefill 56 · TTFT 189.966 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 44 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,05 tok/s TG Prefill 71 · TTFT 28.002 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 45 | Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,94 tok/s TG Prefill 41 · TTFT 62.079 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 46 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,46 tok/s TG Prefill 50 · TTFT 39.304 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 47 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,29 tok/s TG Prefill 62 · TTFT 31.435 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 48 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,20 tok/s TG Prefill 86 · TTFT 127.307 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 49 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,18 tok/s TG Prefill 10 · TTFT 226.444 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 50 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,55 tok/s TG Prefill 36 · TTFT 59.044 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 51 | Seed-OSS-36B-Instruct36BByteDance Seed Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,44 tok/s TG Prefill 39 · TTFT 317.771 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 52 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,22 tok/s TG Prefill 54 · TTFT 382.793 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 53 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,16 tok/s TG Prefill 109 · TTFT 186.084 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,62 tok/s TG Prefill 15 · TTFT 156.050 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 55 | OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,44 tok/s TG Prefill 39 · TTFT 324.717 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 56 | Qwen2.5-72B-Instruct72BQwen (Alibaba) Performance benchmarkPerformancetest Small 1.0 | 2,28 tok/s TG Prefill 81 · TTFT 569 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 57 | Qwen2.5-72B-Instruct72BQwen (Alibaba) Performance benchmark | 2,28 tok/s TG Prefill 81 · TTFT 569 ms | 1× | Keine GPU (CPU-only)51x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | godclaw | Details → | |
| 58 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,27 tok/s TG Prefill 62 · TTFT 233.464 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 59 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,13 tok/s TG Prefill 18 · TTFT 117.963 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 60 | Seed-OSS-36B-Instruct36BByteDance Seed Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,63 tok/s TG Prefill 47 · TTFT 45.942 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 61 | OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,57 tok/s TG Prefill 51 · TTFT 47.947 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 62 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,54 tok/s TG Prefill 44 · TTFT 58.023 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 63 | DeepSeek-V4-Flash-284B-A13B284BDeepSeek Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,20 tok/s TG Prefill 14 · TTFT 148.315 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 64 | Llama-3.3-Nemotron-Super-49B-v1.549BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,14 tok/s TG Prefill 21 · TTFT 117.641 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 65 | Nemotron-H-47B-Reasoning-128K47BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,12 tok/s TG Prefill 16 · TTFT 141.049 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 66 | OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,10 tok/s TG Prefill 8 · TTFT 266.668 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 67 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,04 tok/s TG Prefill 137 · TTFT 171.473 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 68 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,99 tok/s TG Prefill 130 · TTFT 172.354 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 69 | Seed-OSS-36B-Instruct36BByteDance Seed Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,97 tok/s TG Prefill 8 · TTFT 240.790 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 70 | MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,84 tok/s TG Prefill 22 · TTFT 98.716 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 71 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,58 tok/s TG Prefill 77 · TTFT 216.585 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 72 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,27 tok/s TG Prefill 81 · TTFT 206.882 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 73 | Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,27 tok/s TG Prefill 82 · TTFT 204.776 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 74 | Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,25 tok/s TG Prefill 75 · TTFT 202.135 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 75 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,05 tok/s TG Prefill 20 · TTFT 267.436 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 76 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,04 tok/s TG Prefill 29 · TTFT 211.132 ms | 5× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 77 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,03 tok/s TG Prefill 28 · TTFT 212.753 ms | 10× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → |