🏆
Rankings
LLM Leaderboard
Real measurements of every tested language model on real, named hardware – rated by raw speed (performance in tokens per second, prefill and time to first token) and by practical task quality in complete agent and chat runs (harness). Pick a benchmark type below or filter by model, maker and hardware to see exactly what is tested and how the results are produced.
⚡ Performance (tok/s)🤖 Harness quality👥 Concurrency🖥️ real hardware
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 500,57 tok/s TG Prefill 5.466 · TTFT 5.230 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 2 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 479,62 tok/s TG Prefill 4.926 · TTFT 22.591 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 3 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 476,88 tok/s TG Prefill 5.163 · TTFT 21.750 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 412,83 tok/s TG Prefill 6.968 · TTFT 24.214 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 404,40 tok/s TG Prefill 6.093 · TTFT 25.028 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 362,62 tok/s TG Prefill 7.057 · TTFT 5.416 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 7 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 342,04 tok/s TG Prefill 3.606 · TTFT 31.087 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 332,31 tok/s TG Prefill 6.040 · TTFT 5.832 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 9 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 298,12 tok/s TG Prefill 5.098 · TTFT 2.468 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 10 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 262,60 tok/s TG Prefill 7.019 · TTFT 5.005 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 11 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 255,67 tok/s TG Prefill 5.060 · TTFT 6.595 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,06 tok/s TG Prefill 6.916 · TTFT 5.459 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 13 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 236,42 tok/s TG Prefill 2.420 · TTFT 46.503 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 14 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 231,99 tok/s TG Prefill 4.682 · TTFT 6.846 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 15 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 230,10 tok/s TG Prefill 4.529 · TTFT 3.536 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 16 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 218,33 tok/s TG Prefill 6.144 · TTFT 7.137 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 17 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 217,39 tok/s TG Prefill 5.705 · TTFT 7.309 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 18 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 213,64 tok/s TG Prefill 5.109 · TTFT 3.267 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 19 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 191,93 tok/s TG Prefill 3.437 · TTFT 9.778 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 20 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 179,05 tok/s TG Prefill 3.577 · TTFT 9.635 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 21 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 153,33 tok/s TG Prefill 5.312 · TTFT 2.861 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 22 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 145,89 tok/s TG Prefill 5.401 · TTFT 3.079 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 23 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 136,50 tok/s TG Prefill 2.927 · TTFT 24.302 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 24 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 131,83 tok/s TG Prefill 3.139 · TTFT 24.027 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 25 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 127,44 tok/s TG Prefill 2.255 · TTFT 14.493 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 26 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 123,88 tok/s TG Prefill 3.783 · TTFT 8.878 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 27 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 121,76 tok/s TG Prefill 2.553 · TTFT 5.654 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 28 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 115,97 tok/s TG Prefill 1.611 · TTFT 17.040 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 29 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,05 tok/s TG Prefill 1.553 · TTFT 18.334 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 95,82 tok/s TG Prefill 1.287 · TTFT 23.009 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 31 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,65 tok/s TG Prefill 1.138 · TTFT 26.056 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,96 tok/s TG Prefill 896 · TTFT 34.530 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 33 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,08 tok/s TG Prefill 2.801 · TTFT 5.144 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 34 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,17 tok/s TG Prefill 3.527 · TTFT 696 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 35 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,80 tok/s TG Prefill 2.181 · TTFT 17.048 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 36 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,79 tok/s TG Prefill 3.116 · TTFT 788 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 37 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,33 tok/s TG Prefill 2.360 · TTFT 1.241 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 65,64 tok/s TG Prefill 1.574 · TTFT 8.128 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 39 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,60 tok/s TG Prefill 2.989 · TTFT 822 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,51 tok/s TG Prefill 3.003 · TTFT 870 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 61,79 tok/s TG Prefill 1.252 · TTFT 11.277 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 42 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,53 tok/s TG Prefill 2.698 · TTFT 913 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 43 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 57,14 tok/s TG Prefill 2.196 · TTFT 1.120 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 44 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 56,90 tok/s TG Prefill 2.282 · TTFT 5.952 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 45 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 56,87 tok/s TG Prefill 2.232 · TTFT 5.794 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 46 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,74 tok/s TG Prefill 2.434 · TTFT 1.009 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 47 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 53,49 tok/s TG Prefill 1.965 · TTFT 7.527 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 48 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 53,24 tok/s TG Prefill 788 · TTFT 17.420 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 49 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,90 tok/s TG Prefill 1.051 · TTFT 13.158 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 50 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 45,31 tok/s TG Prefill 644 · TTFT 217.710 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 51 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 40,22 tok/s TG Prefill 1.445 · TTFT 1.703 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 52 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,94 tok/s TG Prefill 1.472 · TTFT 9.827 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 53 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 35,99 tok/s TG Prefill 2.848 · TTFT 865 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 54 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 34,55 tok/s TG Prefill 2.568 · TTFT 958 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 55 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 30,26 tok/s TG Prefill 1.500 · TTFT 1.640 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 56 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,74 tok/s TG Prefill 1.088 · TTFT 2.257 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 57 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,62 tok/s TG Prefill 706 · TTFT 3.492 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 58 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,09 tok/s TG Prefill 1.210 · TTFT 2.034 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 59 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,71 tok/s TG Prefill 662 · TTFT 64.391 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 60 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,20 tok/s TG Prefill 1.548 · TTFT 1.551 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 61 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 21,20 tok/s TG Prefill 1.548 · TTFT 1.551 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 62 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 20,90 tok/s TG Prefill 572 · TTFT 7.773 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 63 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,27 tok/s TG Prefill 434 · TTFT 5.669 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 64 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,21 tok/s TG Prefill 661 · TTFT 3.715 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 65 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,26 tok/s TG Prefill 1.306 · TTFT 1.884 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 66 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,08 tok/s TG Prefill 1.508 · TTFT 1.441 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 67 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 19,08 tok/s TG Prefill 1.508 · TTFT 1.441 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 68 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 18,60 tok/s TG Prefill 615 · TTFT 4.520 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 69 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 17,61 tok/s TG Prefill 1.615 · TTFT 1.528 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 70 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 11,39 tok/s TG Prefill 1.288 · TTFT 1.907 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 71 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,86 tok/s TG Prefill 8.244 · TTFT 264 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 72 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 9,86 tok/s TG Prefill 8.244 · TTFT 264 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 73 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,84 tok/s TG Prefill 7.325 · TTFT 311 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 74 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 9,84 tok/s TG Prefill 7.325 · TTFT 311 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 75 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,50 tok/s TG Prefill 52 · TTFT 186.270 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 76 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,46 tok/s TG Prefill 453 · TTFT 5.425 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 77 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,40 tok/s TG Prefill 50 · TTFT 190.791 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 78 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,39 tok/s TG Prefill 52 · TTFT 186.594 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 79 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,38 tok/s TG Prefill 50 · TTFT 190.807 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 80 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,35 tok/s TG Prefill 50 · TTFT 190.945 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 81 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,27 tok/s TG Prefill 50 · TTFT 190.997 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 82 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,26 tok/s TG Prefill 856 · TTFT 2.877 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 83 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,57 tok/s TG Prefill 4.108 · TTFT 529 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 84 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 5,57 tok/s TG Prefill 4.108 · TTFT 529 ms | 1× | AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 85 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,54 tok/s TG Prefill 5.413 · TTFT 420 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 86 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 5,54 tok/s TG Prefill 5.413 · TTFT 420 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 87 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,30 tok/s TG Prefill 3.582 · TTFT 607 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 88 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 5,30 tok/s TG Prefill 3.582 · TTFT 607 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 89 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,24 tok/s TG Prefill 3.234 · TTFT 701 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 90 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmark | 5,24 tok/s TG Prefill 3.234 · TTFT 701 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 91 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,54 tok/s TG Prefill 38 · TTFT 64.727 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 92 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,43 tok/s TG Prefill 37 · TTFT 66.318 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 93 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,42 tok/s TG Prefill 37 · TTFT 66.278 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → |
