🏆
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 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.683,83 tok/s TG Prefill 10.169 · TTFT 7.361 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 2 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.670,49 tok/s TG Prefill 10.926 · TTFT 7.140 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.521,37 tok/s TG Prefill 12.779 · TTFT 7.364 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 → | |
| 4 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.518,42 tok/s TG Prefill 15.383 · TTFT 7.173 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 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.465,26 tok/s TG Prefill 8.251 · TTFT 8.474 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 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 935,41 tok/s TG Prefill 8.108 · TTFT 2.626 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 7 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 930,61 tok/s TG Prefill 5.307 · TTFT 13.161 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 8 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 926,17 tok/s TG Prefill 9.914 · TTFT 2.386 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 906,04 tok/s TG Prefill 39.029 · TTFT 1.193 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 10 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 883,71 tok/s TG Prefill 12.981 · TTFT 12.917 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 11 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 873,72 tok/s TG Prefill 33.023 · TTFT 1.835 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 12 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 831,96 tok/s TG Prefill 14.114 · TTFT 2.202 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 → | |
| 13 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 816,46 tok/s TG Prefill 11.471 · TTFT 2.674 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 → | |
| 14 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 813,62 tok/s TG Prefill 7.463 · TTFT 2.911 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 → | |
| 15 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 751,67 tok/s TG Prefill 32.340 · TTFT 1.271 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 16 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 673,19 tok/s TG Prefill 30.512 · TTFT 1.156 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 17 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 633,41 tok/s TG Prefill 20.292 · TTFT 767 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 18 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 625,71 tok/s TG Prefill 31.724 · TTFT 396 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 19 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 558,18 tok/s TG Prefill 4.694 · TTFT 4.497 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 20 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 554,20 tok/s TG Prefill 31.733 · TTFT 1.123 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 21 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 543,09 tok/s TG Prefill 12.760 · TTFT 6.794 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 22 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 541,18 tok/s TG Prefill 12.337 · TTFT 6.785 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 23 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 515,25 tok/s TG Prefill 27.809 · TTFT 1.285 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 24 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 508,01 tok/s TG Prefill 28.153 · TTFT 552 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 25 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 487,24 tok/s TG Prefill 12.271 · TTFT 3.758 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 26 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 451,89 tok/s TG Prefill 23.930 · TTFT 658 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 27 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 425,16 tok/s TG Prefill 13.041 · TTFT 8.251 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 28 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 415,85 tok/s TG Prefill 22.897 · TTFT 1.440 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 29 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 402,65 tok/s TG Prefill 13.733 · TTFT 8.247 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 30 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 381,56 tok/s TG Prefill 24.720 · TTFT 634 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 31 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 348,36 tok/s TG Prefill 21.278 · TTFT 737 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 32 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 312,09 tok/s TG Prefill 8.022 · TTFT 304 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 311,81 tok/s TG Prefill 12.222 · TTFT 2.737 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 34 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 310,13 tok/s TG Prefill 6.122 · TTFT 397 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 35 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 305,47 tok/s TG Prefill 11.465 · TTFT 1.138 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 305,07 tok/s TG Prefill 10.847 · TTFT 1.196 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 298,25 tok/s TG Prefill 17.174 · TTFT 825 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 38 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 289,78 tok/s TG Prefill 19.112 · TTFT 1.734 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 39 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 273,14 tok/s TG Prefill 10.441 · TTFT 234 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 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 272,80 tok/s TG Prefill 6.458 · TTFT 377 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 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 258,25 tok/s TG Prefill 6.921 · TTFT 4.438 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 42 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 254,59 tok/s TG Prefill 7.497 · TTFT 4.296 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 251,88 tok/s TG Prefill 9.060 · TTFT 1.512 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 44 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 251,85 tok/s TG Prefill 11.072 · TTFT 2.807 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 45 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 241,10 tok/s TG Prefill 5.388 · TTFT 5.855 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 46 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 233,88 tok/s TG Prefill 10.557 · TTFT 236 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 47 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 221,28 tok/s TG Prefill 8.379 · TTFT 300 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 48 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 217,88 tok/s TG Prefill 12.212 · TTFT 1.286 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 49 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 211,86 tok/s TG Prefill 11.108 · TTFT 1.230 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 50 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 208,21 tok/s TG Prefill 8.805 · TTFT 277 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 → | |
| 51 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 202,60 tok/s TG Prefill 14.302 · TTFT 995 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 52 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 199,74 tok/s TG Prefill 5.200 · TTFT 2.539 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 53 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,76 tok/s TG Prefill 4.024 · TTFT 605 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 54 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 197,83 tok/s TG Prefill 4.807 · TTFT 2.927 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 55 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 191,84 tok/s TG Prefill 5.308 · TTFT 2.484 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 56 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 187,17 tok/s TG Prefill 6.204 · TTFT 713 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 57 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 185,95 tok/s TG Prefill 10.074 · TTFT 1.470 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 58 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 170,28 tok/s TG Prefill 5.820 · TTFT 419 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 59 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 170,21 tok/s TG Prefill 4.865 · TTFT 501 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 60 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,65 tok/s TG Prefill 7.081 · TTFT 345 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 61 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 164,17 tok/s TG Prefill 10.792 · TTFT 226 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 62 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 163,90 tok/s TG Prefill 10.167 · TTFT 240 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 63 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 160,71 tok/s TG Prefill 5.616 · TTFT 435 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 64 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 155,77 tok/s TG Prefill 1.107 · TTFT 76.761 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 65 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 146,14 tok/s TG Prefill 8.972 · TTFT 273 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 66 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 142,29 tok/s TG Prefill 8.666 · TTFT 281 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 67 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 130,41 tok/s TG Prefill 5.467 · TTFT 446 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 68 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 130,03 tok/s TG Prefill 5.868 · TTFT 416 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 69 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 121,25 tok/s TG Prefill 5.620 · TTFT 434 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 70 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 118,04 tok/s TG Prefill 1.033 · TTFT 25.146 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 71 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 111,44 tok/s TG Prefill 6.435 · TTFT 386 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 72 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 98,75 tok/s TG Prefill 2.900 · TTFT 840 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 73 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 91,39 tok/s TG Prefill 4.034 · TTFT 603 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 74 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark | 91,39 tok/s TG Prefill 4.034 · TTFT 603 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 75 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,58 tok/s TG Prefill 4.831 · TTFT 503 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 76 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark | 88,58 tok/s TG Prefill 4.831 · TTFT 503 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 77 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,07 tok/s TG Prefill 2.470 · TTFT 1.034 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 78 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,84 tok/s TG Prefill 2.455 · TTFT 1.018 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 79 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark | 87,84 tok/s TG Prefill 2.455 · TTFT 1.018 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 80 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,30 tok/s TG Prefill 2.716 · TTFT 900 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 81 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,01 tok/s TG Prefill 236 · TTFT 217.042 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 82 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,97 tok/s TG Prefill 234 · TTFT 217.587 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 83 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,40 tok/s TG Prefill 234 · TTFT 218.247 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 84 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,75 tok/s TG Prefill 902 · TTFT 2.698 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 85 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 51,82 tok/s TG Prefill 198 · TTFT 87.392 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 86 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 51,62 tok/s TG Prefill 199 · TTFT 87.191 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 87 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,98 tok/s TG Prefill 197 · TTFT 88.234 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 88 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,30 tok/s TG Prefill 320 · TTFT 6.725 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 89 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark | 49,30 tok/s TG Prefill 320 · TTFT 6.725 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 90 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 48,40 tok/s TG Prefill 3.509 · TTFT 649 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 91 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark | 48,40 tok/s TG Prefill 3.509 · TTFT 649 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 92 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 42,04 tok/s TG Prefill 3.904 · TTFT 581 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 93 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark | 42,04 tok/s TG Prefill 3.904 · TTFT 581 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 94 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 41,95 tok/s TG Prefill 8.044 · TTFT 378 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 95 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark | 41,95 tok/s TG Prefill 8.044 · TTFT 378 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 96 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 41,87 tok/s TG Prefill 1.695 · TTFT 20.797 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 97 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 41,21 tok/s TG Prefill 5.446 · TTFT 460 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 98 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark | 41,21 tok/s TG Prefill 5.446 · TTFT 460 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 99 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,62 tok/s TG Prefill 1.223 · TTFT 11.695 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 100 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,53 tok/s TG Prefill 177 · TTFT 13.826 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 101 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,46 tok/s TG Prefill 176 · TTFT 13.902 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 102 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,17 tok/s TG Prefill 174 · TTFT 14.034 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 103 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 14,82 tok/s TG Prefill 509 · TTFT 4.908 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 104 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,52 tok/s TG Prefill 71 · TTFT 152.830 ms | 5× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 105 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,64 tok/s TG Prefill 73 · TTFT 33.548 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 106 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,58 tok/s TG Prefill 77 · TTFT 216.585 ms | 10× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → |
