🏆
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 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 952,78 tok/s TG Prefill 20.106 · TTFT 1.542 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 2 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 854,00 tok/s TG Prefill 11.767 · TTFT 917 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 3 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 845,94 tok/s TG Prefill 12.772 · TTFT 775 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 4 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 841,72 tok/s TG Prefill 14.604 · TTFT 678 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 5 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 841,61 tok/s TG Prefill 14.924 · TTFT 662 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 6 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,88 tok/s TG Prefill 17.307 · TTFT 1.172 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 7 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,69 tok/s TG Prefill 16.223 · TTFT 1.254 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 8 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,46 tok/s TG Prefill 17.541 · TTFT 1.168 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 9 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 761,43 tok/s TG Prefill 16.543 · TTFT 1.234 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 10 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 596,47 tok/s TG Prefill 26.540 · TTFT 369 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 11 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,68 tok/s TG Prefill 6.583 · TTFT 3.083 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 12 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,13 tok/s TG Prefill 6.578 · TTFT 3.087 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 13 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,28 tok/s TG Prefill 6.578 · TTFT 3.088 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 14 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 465,30 tok/s TG Prefill 6.571 · TTFT 3.092 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 15 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,09 tok/s TG Prefill 5.846 · TTFT 1.696 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 16 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,88 tok/s TG Prefill 5.828 · TTFT 1.704 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 17 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,92 tok/s TG Prefill 5.882 · TTFT 1.688 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 18 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,70 tok/s TG Prefill 5.893 · TTFT 1.686 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 19 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 398,29 tok/s TG Prefill 2.733 · TTFT 840 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 20 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 398,01 tok/s TG Prefill 10.596 · TTFT 187 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 21 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 397,74 tok/s TG Prefill 10.726 · TTFT 184 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 22 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 397,32 tok/s TG Prefill 7.323 · TTFT 270 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 23 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,36 tok/s TG Prefill 5.532 · TTFT 357 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 24 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,86 tok/s TG Prefill 5.555 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 25 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,52 tok/s TG Prefill 5.502 · TTFT 360 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 26 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,97 tok/s TG Prefill 5.542 · TTFT 357 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 27 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 206,91 tok/s TG Prefill 2.708 · TTFT 3.698 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 195,04 tok/s TG Prefill 8.425 · TTFT 231 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 29 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 188,81 tok/s TG Prefill 3.560 · TTFT 6.336 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 103,16 tok/s TG Prefill 1.485 · TTFT 15.094 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 100,40 tok/s TG Prefill 1.128 · TTFT 8.829 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 91,77 tok/s TG Prefill 1.236 · TTFT 16.438 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,43 tok/s TG Prefill 1.238 · TTFT 16.400 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 84,58 tok/s TG Prefill 1.112 · TTFT 8.944 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,72 tok/s TG Prefill 1.115 · TTFT 8.920 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 80,01 tok/s TG Prefill 1.237 · TTFT 16.434 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,61 tok/s TG Prefill 1.233 · TTFT 16.469 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,36 tok/s TG Prefill 2.286 · TTFT 843 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 39 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 76,81 tok/s TG Prefill 1.115 · TTFT 8.925 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,94 tok/s TG Prefill 1.105 · TTFT 8.985 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,58 tok/s TG Prefill 1.297 · TTFT 1.648 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 42 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 61,36 tok/s TG Prefill 3.405 · TTFT 6.013 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 → | |
| 43 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,79 tok/s TG Prefill 2.291 · TTFT 889 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 44 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,22 tok/s TG Prefill 2.896 · TTFT 3.418 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 → | |
| 45 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,14 tok/s TG Prefill 2.918 · TTFT 3.390 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 → | |
| 46 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,06 tok/s TG Prefill 2.857 · TTFT 3.468 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 → | |
| 47 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 57,10 tok/s TG Prefill 3.279 · TTFT 6.208 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 → | |
| 48 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 57,01 tok/s TG Prefill 3.263 · TTFT 6.211 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 → | |
| 49 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 56,94 tok/s TG Prefill 3.350 · TTFT 6.080 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 → | |
| 50 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 55,99 tok/s TG Prefill 3.520 · TTFT 622 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 51 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 55,94 tok/s TG Prefill 3.219 · TTFT 6.322 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 → | |
| 52 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 55,28 tok/s TG Prefill 3.088 · TTFT 6.584 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 → | |
| 53 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 55,20 tok/s TG Prefill 3.255 · TTFT 6.226 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 → | |
| 54 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,58 tok/s TG Prefill 3.224 · TTFT 6.323 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 → | |
| 55 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 53,70 tok/s TG Prefill 1.005 · TTFT 1.925 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 56 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,67 tok/s TG Prefill 2.704 · TTFT 3.670 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 → | |
| 57 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,14 tok/s TG Prefill 1.113 · TTFT 1.779 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 58 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,10 tok/s TG Prefill 1.109 · TTFT 1.784 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 59 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,84 tok/s TG Prefill 1.112 · TTFT 1.778 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 60 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,59 tok/s TG Prefill 1.118 · TTFT 1.769 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 61 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,49 tok/s TG Prefill 2.824 · TTFT 3.508 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 → | |
| 62 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 34,21 tok/s TG Prefill 5.971 · TTFT 356 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 63 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,19 tok/s TG Prefill 2.767 · TTFT 1.132 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 64 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,73 tok/s TG Prefill 816 · TTFT 35.129 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 65 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,81 tok/s TG Prefill 2.530 · TTFT 3.935 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 → | |
| 66 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,48 tok/s TG Prefill 2.547 · TTFT 3.908 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 → | |
| 67 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,63 tok/s TG Prefill 2.467 · TTFT 4.025 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 → | |
| 68 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 18,94 tok/s TG Prefill 516 · TTFT 20.783 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 69 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,34 tok/s TG Prefill 1.968 · TTFT 1.004 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 → | |
| 70 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,34 tok/s TG Prefill 1.963 · TTFT 1.006 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 → | |
| 71 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,34 tok/s TG Prefill 1.969 · TTFT 1.003 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 → | |
| 72 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,33 tok/s TG Prefill 1.959 · TTFT 1.008 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 → | |
| 73 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,33 tok/s TG Prefill 1.959 · TTFT 1.008 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 → | |
| 74 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,75 tok/s TG Prefill 1.419 · TTFT 1.714 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 → | |
| 75 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,85 tok/s TG Prefill 1.623 · TTFT 1.259 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 → | |
| 76 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,99 tok/s TG Prefill 1.421 · TTFT 1.571 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 → | |
| 77 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,61 tok/s TG Prefill 342 · TTFT 5.738 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 78 | Qwen3.6-35B-A3BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,29 tok/s TG Prefill 62 · TTFT 31.435 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → |
