🏆
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 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.743,96 tok/s TG Prefill 13.641 · TTFT 5.790 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.743,14 tok/s TG Prefill 12.148 · TTFT 5.881 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.608,46 tok/s TG Prefill 31.452 · TTFT 1.633 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 4 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.210,29 tok/s TG Prefill 9.745 · TTFT 8.399 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.196,98 tok/s TG Prefill 6.074 · TTFT 10.280 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.082,39 tok/s TG Prefill 6.941 · TTFT 9.659 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 7 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.022,79 tok/s TG Prefill 18.744 · TTFT 2.204 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 8 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.009,04 tok/s TG Prefill 4.090 · TTFT 12.734 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 9 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 973,54 tok/s TG Prefill 23.599 · TTFT 460 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 10 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 971,35 tok/s TG Prefill 9.983 · TTFT 2.015 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 11 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 969,62 tok/s TG Prefill 12.437 · TTFT 1.852 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 913,39 tok/s TG Prefill 8.119 · TTFT 11.247 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 13 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 883,39 tok/s TG Prefill 5.377 · TTFT 12.467 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 14 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 710,36 tok/s TG Prefill 8.954 · TTFT 2.695 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 15 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 702,86 tok/s TG Prefill 5.157 · TTFT 6.385 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 16 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 677,50 tok/s TG Prefill 2.978 · TTFT 18.549 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 17 | Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 676,42 tok/s TG Prefill 5.367 · TTFT 3.579 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 18 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 616,01 tok/s TG Prefill 13.778 · TTFT 803 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 19 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 592,13 tok/s TG Prefill 5.662 · TTFT 3.385 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 20 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 590,01 tok/s TG Prefill 5.490 · TTFT 17.999 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 21 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 585,92 tok/s TG Prefill 3.535 · TTFT 4.487 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 22 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 505,77 tok/s TG Prefill 5.745 · TTFT 7.265 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 23 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 497,64 tok/s TG Prefill 8.340 · TTFT 5.360 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 24 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 489,71 tok/s TG Prefill 8.631 · TTFT 3.252 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 25 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 486,20 tok/s TG Prefill 4.345 · TTFT 5.863 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 26 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,02 tok/s TG Prefill 4.949 · TTFT 4.084 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 360,92 tok/s TG Prefill 2.636 · TTFT 6.319 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 28 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 344,13 tok/s TG Prefill 3.766 · TTFT 5.354 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 29 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 343,93 tok/s TG Prefill 2.544 · TTFT 7.919 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 329,94 tok/s TG Prefill 3.647 · TTFT 5.519 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 323,15 tok/s TG Prefill 3.285 · TTFT 3.021 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 323,12 tok/s TG Prefill 5.337 · TTFT 5.911 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 33 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 322,77 tok/s TG Prefill 5.717 · TTFT 5.160 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 319,92 tok/s TG Prefill 3.167 · TTFT 3.125 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 35 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 319,02 tok/s TG Prefill 1.498 · TTFT 42.331 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 318,94 tok/s TG Prefill 1.446 · TTFT 42.781 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 318,66 tok/s TG Prefill 5.742 · TTFT 2.122 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 38 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 318,47 tok/s TG Prefill 1.427 · TTFT 42.816 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 318,17 tok/s TG Prefill 1.479 · TTFT 42.546 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 316,35 tok/s TG Prefill 1.470 · TTFT 42.801 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 316,28 tok/s TG Prefill 1.496 · TTFT 42.551 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 315,66 tok/s TG Prefill 3.728 · TTFT 2.722 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 43 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 312,21 tok/s TG Prefill 5.010 · TTFT 5.594 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 44 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 309,02 tok/s TG Prefill 1.120 · TTFT 42.243 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 45 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 306,90 tok/s TG Prefill 2.293 · TTFT 4.306 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 46 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 296,15 tok/s TG Prefill 4.336 · TTFT 4.376 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 47 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 293,98 tok/s TG Prefill 2.069 · TTFT 9.136 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 48 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 289,48 tok/s TG Prefill 11.717 · TTFT 3.710 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 49 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 279,96 tok/s TG Prefill 4.128 · TTFT 2.405 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 50 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 279,88 tok/s TG Prefill 6.465 · TTFT 4.568 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 51 | Qwen3-Coder-30B-A3B-Instruct30BQwen (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.cppgodclawQ4_K_M | Details → | |
| 52 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 276,90 tok/s TG Prefill 3.500 · TTFT 5.729 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 53 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 276,28 tok/s TG Prefill 9.272 · TTFT 213 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 272,78 tok/s TG Prefill 1.270 · TTFT 14.950 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 55 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 271,15 tok/s TG Prefill 1.523 · TTFT 12.453 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 56 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 267,70 tok/s TG Prefill 6.847 · TTFT 4.383 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 57 | Qwen3-30B-A3B-Instruct-250730BQwen (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.cppgodclawQ4_K_M | Details → | |
| 58 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 263,50 tok/s TG Prefill 3.150 · TTFT 4.792 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 59 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 263,34 tok/s TG Prefill 784 · TTFT 55.800 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 60 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 262,93 tok/s TG Prefill 8.472 · TTFT 4.535 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 61 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 262,45 tok/s TG Prefill 811 · TTFT 55.388 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 62 | Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 262,44 tok/s TG Prefill 822 · TTFT 55.319 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 63 | Qwen3-Coder-30B-A3B-Instruct30BQwen (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.cppgodclawQ8_0 | Details → | |
| 64 | 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 → | |
| 65 | Qwen3-Coder-30B-A3B-Instruct30BQwen (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.cppgodclawQ4_K_M | Details → | |
| 66 | 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 → | |
| 67 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 253,35 tok/s TG Prefill 5.135 · TTFT 1.933 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 68 | Qwen3-30B-A3B-Instruct-250730BQwen (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.cppgodclawQ8_0 | Details → | |
| 69 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 247,30 tok/s TG Prefill 3.039 · TTFT 6.513 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 70 | Qwen3-30B-A3B-Instruct-250730BQwen (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.cppgodclawQ4_K_M | Details → | |
| 71 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,10 tok/s TG Prefill 5.881 · TTFT 4.862 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 72 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,12 tok/s TG Prefill 2.809 · TTFT 7.040 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 73 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 243,46 tok/s TG Prefill 2.311 · TTFT 25.408 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 74 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 242,32 tok/s TG Prefill 6.971 · TTFT 284 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 75 | 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 → | |
| 76 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 239,26 tok/s TG Prefill 2.309 · TTFT 8.469 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 77 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 238,53 tok/s TG Prefill 6.897 · TTFT 1.885 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 78 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 235,51 tok/s TG Prefill 2.971 · TTFT 16.110 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 79 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 235,12 tok/s TG Prefill 3.475 · TTFT 6.384 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 80 | Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 233,69 tok/s TG Prefill 2.376 · TTFT 950 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 81 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 233,01 tok/s TG Prefill 6.125 · TTFT 5.956 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 82 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 228,18 tok/s TG Prefill 11.075 · TTFT 179 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 83 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 226,73 tok/s TG Prefill 2.419 · TTFT 11.596 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 84 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 226,27 tok/s TG Prefill 3.118 · TTFT 3.181 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 85 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 223,59 tok/s TG Prefill 2.319 · TTFT 10.040 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 86 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 222,74 tok/s TG Prefill 5.246 · TTFT 5.445 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 87 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 218,82 tok/s TG Prefill 3.287 · TTFT 5.954 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 88 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 218,77 tok/s TG Prefill 1.680 · TTFT 11.308 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 89 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 216,16 tok/s TG Prefill 1.128 · TTFT 8.806 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 90 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 214,82 tok/s TG Prefill 3.547 · TTFT 7.908 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 91 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 212,47 tok/s TG Prefill 1.988 · TTFT 11.157 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 92 | Qwen3-Coder-30B-A3B-Instruct30BQwen (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.cppgodclawQ4_K_M | Details → | |
| 93 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 211,78 tok/s TG Prefill 3.317 · TTFT 6.868 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 94 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 211,46 tok/s TG Prefill 2.663 · TTFT 8.403 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 95 | Qwen3-Coder-30B-A3B-Instruct30BQwen (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.cppgodclawQ8_0 | Details → | |
| 96 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 209,75 tok/s TG Prefill 1.247 · TTFT 16.274 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 97 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 209,69 tok/s TG Prefill 4.186 · TTFT 4.508 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 98 | Qwen3-30B-A3B-Instruct-250730BQwen (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.cppgodclawQ4_K_M | Details → | |
| 99 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 206,48 tok/s TG Prefill 3.217 · TTFT 7.108 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 100 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 205,68 tok/s TG Prefill 3.174 · TTFT 3.129 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 101 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 205,50 tok/s TG Prefill 1.351 · TTFT 15.992 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 102 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 205,12 tok/s TG Prefill 5.797 · TTFT 5.426 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 103 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 205,02 tok/s TG Prefill 1.348 · TTFT 16.034 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 104 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 205,02 tok/s TG Prefill 1.327 · TTFT 16.066 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 105 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,64 tok/s TG Prefill 13.127 · TTFT 2.817 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 106 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,44 tok/s TG Prefill 1.300 · TTFT 16.378 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 107 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,31 tok/s TG Prefill 1.375 · TTFT 15.932 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 108 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,28 tok/s TG Prefill 2.468 · TTFT 9.078 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 109 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,26 tok/s TG Prefill 2.556 · TTFT 8.711 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 110 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,18 tok/s TG Prefill 5.112 · TTFT 2.507 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 111 | Qwen3-30B-A3B-Instruct-250730BQwen (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.cppgodclawQ8_0 | Details → | |
| 112 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 203,41 tok/s TG Prefill 1.372 · TTFT 16.012 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 113 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 201,99 tok/s TG Prefill 1.186 · TTFT 16.972 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 114 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 201,53 tok/s TG Prefill 2.489 · TTFT 8.976 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 115 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 201,38 tok/s TG Prefill 4.258 · TTFT 2.272 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 116 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 201,02 tok/s TG Prefill 13.392 · TTFT 2.808 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 117 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 200,47 tok/s TG Prefill 5.590 · TTFT 2.527 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 118 | 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 → | |
| 119 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,63 tok/s TG Prefill 5.420 · TTFT 2.546 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 120 | 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 → | |
| 121 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 197,82 tok/s TG Prefill 3.730 · TTFT 3.658 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 122 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 195,94 tok/s TG Prefill 3.019 · TTFT 3.323 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 123 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 194,91 tok/s TG Prefill 2.312 · TTFT 11.972 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 124 | Qwen3-Coder-30B-A3B-Instruct30BQwen (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.cppgodclawQ4_K_M | Details → | |
| 125 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 194,57 tok/s TG Prefill 2.108 · TTFT 4.741 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 126 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 193,40 tok/s TG Prefill 2.117 · TTFT 4.707 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 127 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 192,64 tok/s TG Prefill 2.920 · TTFT 3.432 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 128 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 191,85 tok/s TG Prefill 1.344 · TTFT 15.099 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 129 | 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 → | |
| 130 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 191,23 tok/s TG Prefill 1.903 · TTFT 11.602 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 131 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 189,07 tok/s TG Prefill 3.110 · TTFT 638 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_XL | Details → | |
| 132 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 188,33 tok/s TG Prefill 1.184 · TTFT 17.577 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 133 | Qwen3-30B-A3B-Instruct-250730BQwen (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.cppgodclawQ4_K_M | Details → | |
| 134 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 184,38 tok/s TG Prefill 940 · TTFT 16.001 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 135 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 184,04 tok/s TG Prefill 1.777 · TTFT 5.487 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 136 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 183,53 tok/s TG Prefill 1.935 · TTFT 5.145 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 137 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 182,16 tok/s TG Prefill 1.440 · TTFT 6.875 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 138 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 182,10 tok/s TG Prefill 1.903 · TTFT 6.524 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 139 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 179,04 tok/s TG Prefill 2.033 · TTFT 4.903 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 140 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 178,74 tok/s TG Prefill 9.274 · TTFT 1.816 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 141 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 175,20 tok/s TG Prefill 3.098 · TTFT 3.204 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 142 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 172,91 tok/s TG Prefill 2.730 · TTFT 3.618 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 143 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 172,69 tok/s TG Prefill 2.964 · TTFT 3.184 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 144 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 170,96 tok/s TG Prefill 2.383 · TTFT 4.068 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 145 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 170,69 tok/s TG Prefill 2.902 · TTFT 11.434 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 146 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,98 tok/s TG Prefill 1.029 · TTFT 69.564 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 147 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,28 tok/s TG Prefill 3.412 · TTFT 2.850 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 148 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 167,79 tok/s TG Prefill 1.706 · TTFT 11.878 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 149 | Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 165,70 tok/s TG Prefill 2.126 · TTFT 11.893 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 150 | Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 165,38 tok/s TG Prefill 2.122 · TTFT 11.901 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 151 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 165,04 tok/s TG Prefill 2.897 · TTFT 711 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 152 | Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 164,72 tok/s TG Prefill 2.120 · TTFT 11.924 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 153 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 163,29 tok/s TG Prefill 3.551 · TTFT 3.722 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 154 | Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 163,13 tok/s TG Prefill 683 · TTFT 22.415 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 155 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 163,13 tok/s TG Prefill 684 · TTFT 22.434 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 156 | Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 162,55 tok/s TG Prefill 715 · TTFT 21.986 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 157 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 162,37 tok/s TG Prefill 2.995 · TTFT 7.467 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 158 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 159,48 tok/s TG Prefill 4.475 · TTFT 2.882 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 159 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 159,03 tok/s TG Prefill 110 · TTFT 25.408 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 160 | Qwen3-Coder-30B-A3B-Instruct30BQwen (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.cppgodclawQ4_K_M | Details → | |
| 161 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 156,61 tok/s TG Prefill 3.757 · TTFT 4.751 ms | 10× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 162 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 156,19 tok/s TG Prefill 2.436 · TTFT 3.874 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 163 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 155,85 tok/s TG Prefill 1.036 · TTFT 78.057 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 164 | 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 → | |
| 165 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 154,77 tok/s TG Prefill 4.675 · TTFT 3.232 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 166 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 154,68 tok/s TG Prefill 1.896 · TTFT 1.046 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 167 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 153,96 tok/s TG Prefill 1.395 · TTFT 74.722 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 168 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 152,96 tok/s TG Prefill 891 · TTFT 26.016 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 169 | Qwen3-30B-A3B-Instruct-250730BQwen (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.cppgodclawQ4_K_M | Details → | |
| 170 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 152,42 tok/s TG Prefill 5.042 · TTFT 3.214 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 171 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 152,07 tok/s TG Prefill 1.734 · TTFT 18.061 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 172 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 150,36 tok/s TG Prefill 1.880 · TTFT 17.241 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 173 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 149,63 tok/s TG Prefill 8.218 · TTFT 3.485 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ-INT4 | Details → | |
| 174 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 147,45 tok/s TG Prefill 1.813 · TTFT 17.552 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawIQ4_XS | Details → | |
| 175 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 146,19 tok/s TG Prefill 6.653 · TTFT 2.534 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 176 | gemma-4-E4B-it8BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 144,58 tok/s TG Prefill 7.078 · TTFT 281 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 177 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 143,29 tok/s TG Prefill 1.967 · TTFT 20.264 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 178 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 142,87 tok/s TG Prefill 498 · TTFT 91.483 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 179 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 142,20 tok/s TG Prefill 503 · TTFT 90.967 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 180 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 141,93 tok/s TG Prefill 1.385 · TTFT 19.489 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 181 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 141,74 tok/s TG Prefill 3.097 · TTFT 9.194 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 182 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 141,60 tok/s TG Prefill 2.423 · TTFT 839 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 183 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 140,90 tok/s TG Prefill 2.783 · TTFT 1.005 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 184 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 140,33 tok/s TG Prefill 2.577 · TTFT 4.812 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 185 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 140,11 tok/s TG Prefill 524 · TTFT 90.775 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 186 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 138,94 tok/s TG Prefill 4.212 · TTFT 8.113 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 187 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 138,90 tok/s TG Prefill 3.102 · TTFT 4.748 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 188 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 138,64 tok/s TG Prefill 2.341 · TTFT 874 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 189 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 138,44 tok/s TG Prefill 1.562 · TTFT 19.650 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 190 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 137,99 tok/s TG Prefill 2.682 · TTFT 738 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 191 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 137,47 tok/s TG Prefill 5.577 · TTFT 8.649 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 192 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 136,80 tok/s TG Prefill 3.720 · TTFT 8.188 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 193 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 134,78 tok/s TG Prefill 2.304 · TTFT 4.417 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 194 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 134,63 tok/s TG Prefill 2.084 · TTFT 13.635 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 195 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 134,52 tok/s TG Prefill 1.360 · TTFT 24.430 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 196 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 133,11 tok/s TG Prefill 1.768 · TTFT 18.406 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 197 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 132,34 tok/s TG Prefill 2.522 · TTFT 3.929 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 198 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 131,94 tok/s TG Prefill 3.904 · TTFT 521 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 199 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 131,37 tok/s TG Prefill 2.411 · TTFT 12.631 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 200 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 130,99 tok/s TG Prefill 2.572 · TTFT 12.677 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 201 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 130,71 tok/s TG Prefill 3.496 · TTFT 13.343 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 202 | Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 130,60 tok/s TG Prefill 1.824 · TTFT 6.739 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 203 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 130,59 tok/s TG Prefill 3.587 · TTFT 13.505 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 204 | Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 129,87 tok/s TG Prefill 1.825 · TTFT 6.733 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 205 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 129,00 tok/s TG Prefill 3.247 · TTFT 594 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 206 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 128,86 tok/s TG Prefill 2.698 · TTFT 734 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 207 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 127,71 tok/s TG Prefill 1.369 · TTFT 22.194 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 208 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 127,52 tok/s TG Prefill 1.724 · TTFT 7.120 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 209 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 127,28 tok/s TG Prefill 1.097 · TTFT 28.208 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 210 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 127,27 tok/s TG Prefill 1.947 · TTFT 14.530 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 211 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 126,92 tok/s TG Prefill 1.616 · TTFT 7.001 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 212 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 124,50 tok/s TG Prefill 4.431 · TTFT 5.687 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 213 | Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 124,22 tok/s TG Prefill 3.730 · TTFT 3.296 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 214 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 123,66 tok/s TG Prefill 2.453 · TTFT 6.575 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawIQ4_XS | Details → | |
| 215 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 123,33 tok/s TG Prefill 1.762 · TTFT 18.471 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 216 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 122,80 tok/s TG Prefill 2.638 · TTFT 3.921 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 217 | Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 122,10 tok/s TG Prefill 10.048 · TTFT 1.358 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 218 | Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 122,07 tok/s TG Prefill 3.576 · TTFT 3.191 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 219 | Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 121,19 tok/s TG Prefill 9.219 · TTFT 1.374 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 220 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 120,47 tok/s TG Prefill 2.594 · TTFT 19.870 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 221 | gemma-4-12B-it12BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 120,20 tok/s TG Prefill 1.360 · TTFT 7.318 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 222 | Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 119,81 tok/s TG Prefill 1.314 · TTFT 21.514 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 223 | Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 119,78 tok/s TG Prefill 1.913 · TTFT 6.365 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 224 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 119,65 tok/s TG Prefill 1.469 · TTFT 9.597 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 225 | Qwen3-Coder-30B-A3B-Instruct30BQwen (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.cppgodclawQ4_K_M | Details → | |
| 226 | North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 118,36 tok/s TG Prefill 895 · TTFT 23.355 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 227 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 118,31 tok/s TG Prefill 1.356 · TTFT 9.496 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 228 | 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 → | |
| 229 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 117,91 tok/s TG Prefill 941 · TTFT 26.171 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 230 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 117,14 tok/s TG Prefill 2.985 · TTFT 3.411 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 231 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 116,57 tok/s TG Prefill 1.336 · TTFT 23.791 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 232 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 116,54 tok/s TG Prefill 1.812 · TTFT 19.077 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 233 | Qwen3-30B-A3B-Instruct-250730BQwen (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.cppgodclawQ4_K_M | Details → | |
| 234 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 115,02 tok/s TG Prefill 1.562 · TTFT 20.338 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 235 | gemma-4-E2B-it5BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 114,56 tok/s TG Prefill 4.326 · TTFT 459 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 236 | Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 111,77 tok/s TG Prefill 847 · TTFT 17.641 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 237 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 111,50 tok/s TG Prefill 1.387 · TTFT 11.441 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 238 | Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 109,93 tok/s TG Prefill 1.922 · TTFT 5.295 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 239 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,50 tok/s TG Prefill 2.121 · TTFT 85.480 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 240 | Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,84 tok/s TG Prefill 645 · TTFT 30.333 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 241 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,05 tok/s TG Prefill 361 · TTFT 137.879 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 242 | Qwen3-Coder-30B-A3B-Instruct30BQwen (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.cppgodclawQ4_K_M | Details → | |
| 243 | Qwen3-30B-A3B-Instruct-250730BQwen (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.cppgodclawQ4_K_M | Details → | |
| 244 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 103,94 tok/s TG Prefill 2.848 · TTFT 64.620 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 245 | Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 103,26 tok/s TG Prefill 2.824 · TTFT 64.279 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 246 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,55 tok/s TG Prefill 2.042 · TTFT 15.214 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 247 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,38 tok/s TG Prefill 1.243 · TTFT 27.006 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 248 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,05 tok/s TG Prefill 1.553 · TTFT 18.334 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 249 | gemma-4-31B-it31BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 101,94 tok/s TG Prefill 176 · TTFT 112.412 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 250 | gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 101,58 tok/s TG Prefill 874 · TTFT 2.364 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → |
