🏆
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-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.671,02 tok/s TG Prefill 11.920 · TTFT 7.068 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 2 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.658,09 tok/s TG Prefill 13.451 · TTFT 6.808 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 3 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.515,72 tok/s TG Prefill 20.491 · TTFT 6.859 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 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.507,51 tok/s TG Prefill 16.412 · TTFT 7.065 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 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.436,00 tok/s TG Prefill 10.085 · TTFT 8.120 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 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 961,53 tok/s TG Prefill 32.305 · TTFT 1.633 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 7 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 931,70 tok/s TG Prefill 11.679 · TTFT 2.264 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 8 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 910,76 tok/s TG Prefill 14.150 · TTFT 2.150 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 9 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 909,25 tok/s TG Prefill 37.116 · TTFT 1.783 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 10 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 905,10 tok/s TG Prefill 7.532 · TTFT 12.527 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 11 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 901,86 tok/s TG Prefill 12.965 · TTFT 12.663 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 12 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 826,52 tok/s TG Prefill 16.141 · TTFT 2.166 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 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 824,71 tok/s TG Prefill 19.971 · TTFT 2.038 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 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 795,25 tok/s TG Prefill 10.892 · TTFT 2.598 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 15 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 655,83 tok/s TG Prefill 17.990 · TTFT 931 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 16 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 649,04 tok/s TG Prefill 17.868 · TTFT 764 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 17 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 542,30 tok/s TG Prefill 6.912 · TTFT 4.026 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 18 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 496,79 tok/s TG Prefill 12.291 · TTFT 3.700 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 19 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 339,73 tok/s TG Prefill 10.614 · TTFT 2.771 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cli | Details → | |
| 20 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 308,49 tok/s TG Prefill 3.931 · TTFT 917 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 21 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 304,63 tok/s TG Prefill 8.163 · TTFT 298 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 22 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 271,12 tok/s TG Prefill 9.743 · TTFT 250 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 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 268,82 tok/s TG Prefill 6.488 · TTFT 376 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 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 268,80 tok/s TG Prefill 10.782 · TTFT 226 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 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 264,15 tok/s TG Prefill 7.432 · TTFT 4.406 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 26 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 260,37 tok/s TG Prefill 8.681 · TTFT 1.498 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cli | Details → | |
| 27 | Qwen3-30B-A3B-Instruct-250730BQ8_0Qwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 251,08 tok/s TG Prefill 5.146 · TTFT 6.222 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 28 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,82 tok/s TG Prefill 4.686 · TTFT 6.831 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 29 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 232,79 tok/s TG Prefill 8.323 · TTFT 311 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 30 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 206,56 tok/s TG Prefill 5.340 · TTFT 2.489 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 31 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,94 tok/s TG Prefill 4.657 · TTFT 527 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 32 | Qwen3-30B-A3B-Instruct-250730BQ8_0Qwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 203,52 tok/s TG Prefill 4.756 · TTFT 2.908 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 33 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 195,39 tok/s TG Prefill 4.296 · TTFT 567 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 34 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 185,99 tok/s TG Prefill 3.624 · TTFT 3.860 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 35 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 169,89 tok/s TG Prefill 7.470 · TTFT 5.007 ms | 10× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppopenclaw_cli | Details → | |
| 36 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,59 tok/s TG Prefill 6.991 · TTFT 350 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 37 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 160,98 tok/s TG Prefill 5.616 · TTFT 434 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cli | Details → | |
| 38 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 152,65 tok/s TG Prefill 1.613 · TTFT 73.900 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 39 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 143,56 tok/s TG Prefill 1.267 · TTFT 4.040 ms | 10× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCL | Details → | |
| 40 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 140,06 tok/s TG Prefill 1.284 · TTFT 1.994 ms | 5× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCL | Details → | |
| 41 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 139,24 tok/s TG Prefill 5.091 · TTFT 2.946 ms | 5× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppopenclaw_cli | Details → | |
| 42 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 115,20 tok/s TG Prefill 1.424 · TTFT 23.184 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 43 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 107,55 tok/s TG Prefill 2.558 · TTFT 11.357 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclaw | Details → | |
| 44 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 105,20 tok/s TG Prefill 2.188 · TTFT 1.113 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 45 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 98,78 tok/s TG Prefill 3.170 · TTFT 771 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 46 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 97,78 tok/s TG Prefill 1.899 · TTFT 6.568 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclaw | Details → | |
| 47 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 97,61 tok/s TG Prefill 2.827 · TTFT 862 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 48 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmark i | 97,61 tok/s TG Prefill 2.827 · TTFT 862 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 49 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 90,98 tok/s TG Prefill 4.283 · TTFT 569 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 50 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmark i | 90,98 tok/s TG Prefill 4.283 · TTFT 569 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 51 | Qwen3-30B-A3B-Instruct-250730BQ8_0Qwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,04 tok/s TG Prefill 2.447 · TTFT 1.039 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 52 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 84,18 tok/s TG Prefill 2.987 · TTFT 816 ms | 1× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppopenclaw_cli | Details → | |
| 53 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 78,90 tok/s TG Prefill 4.644 · TTFT 504 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 54 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmark i | 78,90 tok/s TG Prefill 4.644 · TTFT 504 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 55 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 78,10 tok/s TG Prefill 816 · TTFT 627 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cli batched-bench SYCL | Details → | |
| 56 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 61,65 tok/s TG Prefill 951 · TTFT 2.560 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 57 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 61,26 tok/s TG Prefill 304 · TTFT 211.915 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 58 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 60,90 tok/s TG Prefill 306 · TTFT 211.475 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 59 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 60,80 tok/s TG Prefill 305 · TTFT 212.095 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 60 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,57 tok/s TG Prefill 266 · TTFT 80.738 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 61 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,48 tok/s TG Prefill 267 · TTFT 80.393 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 62 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,44 tok/s TG Prefill 267 · TTFT 80.524 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 63 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 45,43 tok/s TG Prefill 861 · TTFT 2.500 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 64 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmark i | 45,43 tok/s TG Prefill 861 · TTFT 2.500 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 65 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 44,17 tok/s TG Prefill 4.851 · TTFT 489 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 66 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmark i | 44,17 tok/s TG Prefill 4.851 · TTFT 489 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 67 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmark i | 43,75 tok/s TG Prefill 913 · TTFT 2.357 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 68 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 39,27 tok/s TG Prefill 5.443 · TTFT 774 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 69 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmark i | 39,27 tok/s TG Prefill 5.443 · TTFT 774 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 70 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 34,80 tok/s TG Prefill 4.274 · TTFT 570 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 71 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmark i | 34,80 tok/s TG Prefill 4.274 · TTFT 570 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 72 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) i | 32,76 tok/s TG Prefill 4.322 · TTFT 563 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 73 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmark i | 32,76 tok/s TG Prefill 4.322 · TTFT 563 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 74 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,19 tok/s TG Prefill 1.424 · TTFT 20.551 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 75 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,90 tok/s TG Prefill 165 · TTFT 14.853 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 76 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,89 tok/s TG Prefill 162 · TTFT 15.102 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 77 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,54 tok/s TG Prefill 163 · TTFT 15.013 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 78 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,98 tok/s TG Prefill 218 · TTFT 59.755 ms | 5× | Keine GPU (CPU-only)AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 79 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 24,50 tok/s TG Prefill 152 · TTFT 16.071 ms | 1× | Keine GPU (CPU-only)AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 80 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,61 tok/s TG Prefill 1.219 · TTFT 11.738 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 81 | Qwen3-30B-A3B-Instruct-250730BAWQQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,11 tok/s TG Prefill 622 · TTFT 3.910 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 82 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (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.cppgodclaw | Details → | |
| 83 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (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.cppgodclaw | Details → | |
| 84 | Qwen3-30B-A3B-Instruct-250730BQ4_K_MQwen (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.cppgodclaw | Details → |