🏆
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-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.716,59 tok/s TG Prefill 12.604 · TTFT 6.861 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 2 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.689,95 tok/s TG Prefill 14.458 · TTFT 6.609 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 3 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.545,29 tok/s TG Prefill 19.346 · TTFT 6.758 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 4 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.531,89 tok/s TG Prefill 17.119 · TTFT 6.936 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 5 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.455,41 tok/s TG Prefill 11.267 · TTFT 7.904 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 6 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.070,56 tok/s TG Prefill 33.741 · TTFT 976 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 7 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 966,21 tok/s TG Prefill 33.768 · TTFT 1.793 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 8 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 946,70 tok/s TG Prefill 11.668 · TTFT 2.231 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 9 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 938,21 tok/s TG Prefill 13.797 · TTFT 2.113 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 10 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 928,48 tok/s TG Prefill 7.663 · TTFT 12.219 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 11 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 840,36 tok/s TG Prefill 19.755 · TTFT 2.007 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 12 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 837,95 tok/s TG Prefill 16.555 · TTFT 2.123 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 13 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 814,51 tok/s TG Prefill 10.644 · TTFT 2.552 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 14 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 676,76 tok/s TG Prefill 21.675 · TTFT 725 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 15 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 670,65 tok/s TG Prefill 17.357 · TTFT 3.808 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 16 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 554,75 tok/s TG Prefill 7.036 · TTFT 3.930 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 17 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 399,08 tok/s TG Prefill 14.492 · TTFT 984 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 18 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 344,35 tok/s TG Prefill 10.942 · TTFT 2.759 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cli | Details → | |
| 19 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 311,28 tok/s TG Prefill 8.147 · TTFT 299 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 20 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 309,26 tok/s TG Prefill 5.635 · TTFT 432 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 21 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 276,95 tok/s TG Prefill 7.786 · TTFT 4.143 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 22 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 273,64 tok/s TG Prefill 9.644 · TTFT 253 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 23 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 272,24 tok/s TG Prefill 10.423 · TTFT 234 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 24 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 271,59 tok/s TG Prefill 6.698 · TTFT 363 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 25 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 266,26 tok/s TG Prefill 8.447 · TTFT 1.538 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cli | Details → | |
| 26 | Qwen3-Coder-30B-A3B-Instruct30BQ8_0Qwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 258,36 tok/s TG Prefill 5.960 · TTFT 5.584 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 27 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 257,54 tok/s TG Prefill 4.819 · TTFT 6.626 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 28 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 237,20 tok/s TG Prefill 8.070 · TTFT 353 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 29 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 211,94 tok/s TG Prefill 5.476 · TTFT 2.426 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 30 | Qwen3-Coder-30B-A3B-Instruct30BQ8_0Qwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 211,00 tok/s TG Prefill 4.544 · TTFT 2.942 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 31 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,44 tok/s TG Prefill 4.311 · TTFT 565 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 32 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 194,77 tok/s TG Prefill 3.434 · TTFT 3.848 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 33 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 182,87 tok/s TG Prefill 7.295 · TTFT 5.014 ms | 10× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppopenclaw_cli | Details → | |
| 34 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 171,72 tok/s TG Prefill 7.637 · TTFT 319 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 35 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 161,57 tok/s TG Prefill 5.583 · TTFT 437 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cli | Details → | |
| 36 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 157,00 tok/s TG Prefill 1.473 · TTFT 72.295 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 37 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 146,91 tok/s TG Prefill 4.736 · TTFT 2.900 ms | 5× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppopenclaw_cli | Details → | |
| 38 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 118,55 tok/s TG Prefill 1.537 · TTFT 22.290 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 39 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 105,36 tok/s TG Prefill 2.264 · TTFT 1.075 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 40 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 100,05 tok/s TG Prefill 3.211 · TTFT 760 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 41 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 98,95 tok/s TG Prefill 2.674 · TTFT 916 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 42 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 88,22 tok/s TG Prefill 5.195 · TTFT 470 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 43 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmark i | 88,22 tok/s TG Prefill 5.195 · TTFT 470 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 44 | Qwen3-Coder-30B-A3B-Instruct30BQ8_0Qwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,05 tok/s TG Prefill 2.471 · TTFT 1.026 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 45 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,23 tok/s TG Prefill 2.963 · TTFT 824 ms | 1× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppopenclaw_cli | Details → | |
| 46 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 82,49 tok/s TG Prefill 3.953 · TTFT 587 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 47 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmark i | 82,49 tok/s TG Prefill 3.953 · TTFT 587 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 48 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 75,66 tok/s TG Prefill 1.817 · TTFT 2.001 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 49 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmark i | 75,66 tok/s TG Prefill 1.817 · TTFT 2.001 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 50 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,81 tok/s TG Prefill 958 · TTFT 2.541 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 51 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,40 tok/s TG Prefill 329 · TTFT 201.355 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 52 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,01 tok/s TG Prefill 329 · TTFT 202.669 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 53 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,92 tok/s TG Prefill 329 · TTFT 202.414 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 54 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,99 tok/s TG Prefill 291 · TTFT 75.396 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 55 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,46 tok/s TG Prefill 289 · TTFT 75.785 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 56 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,43 tok/s TG Prefill 291 · TTFT 75.557 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 57 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmark i | 47,99 tok/s TG Prefill 867 · TTFT 2.482 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 58 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 47,65 tok/s TG Prefill 5.913 · TTFT 437 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 59 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmark i | 47,65 tok/s TG Prefill 5.913 · TTFT 437 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 60 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 46,52 tok/s TG Prefill 4.080 · TTFT 752 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 61 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmark i | 46,52 tok/s TG Prefill 4.080 · TTFT 752 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 62 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 40,50 tok/s TG Prefill 5.664 · TTFT 755 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 63 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmark i | 40,50 tok/s TG Prefill 5.664 · TTFT 755 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 64 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 39,74 tok/s TG Prefill 3.947 · TTFT 575 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 65 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmark i | 39,74 tok/s TG Prefill 3.947 · TTFT 575 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 66 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 38,34 tok/s TG Prefill 8.377 · TTFT 387 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 67 | Qwen3-Coder-30B-A3B-Instruct30BAWQQwen (Alibaba) Performance benchmark i | 38,34 tok/s TG Prefill 8.377 · TTFT 387 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 68 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,31 tok/s TG Prefill 178 · TTFT 13.748 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 69 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,26 tok/s TG Prefill 178 · TTFT 13.758 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 70 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,06 tok/s TG Prefill 178 · TTFT 13.771 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 71 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (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.cppgodclaw | Details → | |
| 72 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (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.cppgodclaw | Details → | |
| 73 | Qwen3-Coder-30B-A3B-Instruct30BQ4_K_MQwen (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.cppgodclaw | Details → |