🏆
Ranglisten
LLM Leaderboard
Reale Messergebnisse aller getesteten Sprachmodelle auf echter, benannter Hardware – bewertet nach roher Geschwindigkeit (Performance in Token pro Sekunde, Prefill und Zeit bis zum ersten Token) und nach praktischer Aufgaben-Qualität in vollständigen Agenten- und Chat-Abläufen (Harness). Wähle unten einen Benchmark-Typ oder filtere nach Modell, Hersteller und Hardware, um genau zu sehen, was jeweils geprüft wird und wie die Ergebnisse zustande kommen.
⚡ Performance (tok/s)🤖 Harness-Qualität👥 Concurrency🖥️ echte Hardware
| # | Modell / Hersteller | Messwerte | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 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 → | |
| 2 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 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 → | |
| 3 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 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 → | |
| 4 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 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 → | |
| 5 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 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 → | |
| 6 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 7 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 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 → | |
| 8 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 9 | North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 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 → | |
| 10 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 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 → | |
| 11 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 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 → | |
| 12 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 13 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 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 → | |
| 14 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 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 → | |
| 15 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 16 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 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 → | |
| 17 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 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 → | |
| 18 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 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 → | |
| 19 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 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 → | |
| 20 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 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 → | |
| 21 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 22 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 23 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 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 → | |
| 24 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 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 → | |
| 25 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 26 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 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 → | |
| 27 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 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 → | |
| 28 | North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 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 → | |
| 29 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 30 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 31 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 32 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 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 → | |
| 33 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 34 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 35 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 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 → | |
| 36 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 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 → | |
| 37 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 38 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 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 → | |
| 39 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 40 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 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 → | |
| 41 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 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 → | |
| 42 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 43 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 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 → | |
| 44 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 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 → | |
| 45 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 46 | North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 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 → | |
| 47 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 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 → | |
| 48 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 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 → | |
| 49 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 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 → | |
| 50 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 51 | Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 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 → | |
| 52 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 53 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 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 → | |
| 54 | Devstral-Small-250724BMistral AI PerformancebenchmarkTimebench 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 → | |
| 55 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 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 → | |
| 56 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 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 → | |
| 57 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 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 → | |
| 58 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 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 → | |
| 59 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 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 → | |
| 60 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 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 → | |
| 61 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 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 → | |
| 62 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 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 → | |
| 63 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 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 → | |
| 64 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 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 → | |
| 65 | North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 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 → | |
| 66 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 67 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 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 → | |
| 68 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 69 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 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 → | |
| 70 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 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 → | |
| 71 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 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 → | |
| 72 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 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 → | |
| 73 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 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 → | |
| 74 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 101,23 tok/s TG Prefill 5.351 · TTFT 3.702 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 75 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 100,43 tok/s TG Prefill 2.076 · TTFT 5.460 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 76 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 98,68 tok/s TG Prefill 1.242 · TTFT 8.170 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 77 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 98,39 tok/s TG Prefill 2.648 · TTFT 923 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 78 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 94,86 tok/s TG Prefill 1.586 · TTFT 6.256 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 79 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 92,04 tok/s TG Prefill 1.121 · TTFT 21.054 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 80 | Devstral-Small-250724BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 91,82 tok/s TG Prefill 1.642 · TTFT 12.961 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 81 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 90,91 tok/s TG Prefill 2.187 · TTFT 863 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 82 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 90,43 tok/s TG Prefill 1.328 · TTFT 7.107 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 83 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,88 tok/s TG Prefill 5.543 · TTFT 1.786 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 84 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,30 tok/s TG Prefill 4.368 · TTFT 9.029 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 85 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 87,91 tok/s TG Prefill 1.493 · TTFT 6.317 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 86 | North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 85,64 tok/s TG Prefill 2.167 · TTFT 916 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 87 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 85,33 tok/s TG Prefill 2.416 · TTFT 798 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 88 | Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 84,60 tok/s TG Prefill 796 · TTFT 14.144 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 89 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,52 tok/s TG Prefill 2.347 · TTFT 1.048 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 90 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,46 tok/s TG Prefill 2.724 · TTFT 896 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 91 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,37 tok/s TG Prefill 2.737 · TTFT 892 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 92 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,30 tok/s TG Prefill 2.716 · TTFT 900 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 93 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,30 tok/s TG Prefill 2.410 · TTFT 957 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 94 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 81,91 tok/s TG Prefill 2.340 · TTFT 1.052 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 95 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 81,21 tok/s TG Prefill 1.020 · TTFT 11.554 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 96 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 80,66 tok/s TG Prefill 2.359 · TTFT 978 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 97 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,83 tok/s TG Prefill 2.415 · TTFT 799 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 98 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,75 tok/s TG Prefill 1.013 · TTFT 11.630 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 99 | North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,86 tok/s TG Prefill 2.172 · TTFT 912 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 100 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,52 tok/s TG Prefill 1.067 · TTFT 13.620 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 101 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,09 tok/s TG Prefill 3.852 · TTFT 519 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 102 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,45 tok/s TG Prefill 2.015 · TTFT 956 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 103 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 72,25 tok/s TG Prefill 1.990 · TTFT 1.240 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 104 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 71,82 tok/s TG Prefill 1.961 · TTFT 982 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 105 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,89 tok/s TG Prefill 2.286 · TTFT 17.114 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 106 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,80 tok/s TG Prefill 2.181 · TTFT 17.048 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 107 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,31 tok/s TG Prefill 1.997 · TTFT 1.235 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 108 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,19 tok/s TG Prefill 2.207 · TTFT 897 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 109 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,42 tok/s TG Prefill 4.105 · TTFT 597 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 110 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 65,98 tok/s TG Prefill 2.399 · TTFT 825 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 111 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,56 tok/s TG Prefill 4.021 · TTFT 494 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 112 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,37 tok/s TG Prefill 2.232 · TTFT 886 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 113 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,95 tok/s TG Prefill 1.785 · TTFT 1.081 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 114 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,76 tok/s TG Prefill 821 · TTFT 12.234 ms | 5× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 115 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,89 tok/s TG Prefill 1.745 · TTFT 1.106 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 116 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,36 tok/s TG Prefill 661 · TTFT 14.652 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 117 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 61,43 tok/s TG Prefill 1.440 · TTFT 10.139 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 118 | Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 57,65 tok/s TG Prefill 1.849 · TTFT 17.975 ms | 10× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 119 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,72 tok/s TG Prefill 2.235 · TTFT 1.090 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 120 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,09 tok/s TG Prefill 1.557 · TTFT 1.455 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 121 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,80 tok/s TG Prefill 1.555 · TTFT 1.457 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 122 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,42 tok/s TG Prefill 1.172 · TTFT 1.691 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 123 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,24 tok/s TG Prefill 3.416 · TTFT 5.086 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 124 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,18 tok/s TG Prefill 1.183 · TTFT 1.672 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 125 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,20 tok/s TG Prefill 1.206 · TTFT 1.877 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 126 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 43,40 tok/s TG Prefill 1.066 · TTFT 2.179 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 127 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 41,89 tok/s TG Prefill 1.110 · TTFT 1.590 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 128 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 40,86 tok/s TG Prefill 1.094 · TTFT 1.814 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 129 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 40,09 tok/s TG Prefill 2.094 · TTFT 943 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 130 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 39,59 tok/s TG Prefill 2.033 · TTFT 986 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 131 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,94 tok/s TG Prefill 1.472 · TTFT 9.827 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 132 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,93 tok/s TG Prefill 1.679 · TTFT 9.606 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 133 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 34,53 tok/s TG Prefill 2.874 · TTFT 857 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 134 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,39 tok/s TG Prefill 5.134 · TTFT 1.838 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 135 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,54 tok/s TG Prefill 806 · TTFT 3.373 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 136 | Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 30,88 tok/s TG Prefill 1.520 · TTFT 10.032 ms | 5× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 137 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,63 tok/s TG Prefill 582 · TTFT 3.807 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 138 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 28,04 tok/s TG Prefill 604 · TTFT 3.801 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 139 | Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 28,02 tok/s TG Prefill 598 · TTFT 3.766 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 140 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,98 tok/s TG Prefill 604 · TTFT 3.558 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 141 | Devstral-Small-250724BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,76 tok/s TG Prefill 945 · TTFT 3.652 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 142 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,69 tok/s TG Prefill 600 · TTFT 3.579 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 143 | Codestral-22B-v0.122BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,55 tok/s TG Prefill 607 · TTFT 4.493 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 144 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,90 tok/s TG Prefill 570 · TTFT 3.308 ms | 1× | AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 145 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,75 tok/s TG Prefill 523 · TTFT 3.693 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 146 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 10,00 tok/s TG Prefill 1.583 · TTFT 1.597 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 147 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,29 tok/s TG Prefill 858 · TTFT 2.871 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 148 | Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,26 tok/s TG Prefill 856 · TTFT 2.877 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → | |
| 149 | Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,65 tok/s TG Prefill 702 · TTFT 3.160 ms | 1× | 2x AMD Radeon PRO W7800 48GBAMD Ryzen Threadripper PRO 5975WX 32-Cores · 62 GB RAM | vLLMgodclawAWQ | Details → |
