🏆
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 | Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,61 tok/s TG Prefill 4.836 · TTFT 11.175 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 465,47 tok/s TG Prefill 8.435 · TTFT 2.408 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 3 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 455,35 tok/s TG Prefill 8.245 · TTFT 2.462 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 450,54 tok/s TG Prefill 3.632 · TTFT 14.999 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 447,00 tok/s TG Prefill 3.645 · TTFT 15.139 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 357,72 tok/s TG Prefill 4.799 · TTFT 4.228 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 7 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 347,49 tok/s TG Prefill 4.656 · TTFT 4.348 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 331,51 tok/s TG Prefill 6.908 · TTFT 1.433 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 324,87 tok/s TG Prefill 7.451 · TTFT 4.042 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 10 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 321,67 tok/s TG Prefill 7.148 · TTFT 4.460 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 11 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 316,40 tok/s TG Prefill 7.121 · TTFT 1.391 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 12 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 315,53 tok/s TG Prefill 2.703 · TTFT 7.505 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 13 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 314,82 tok/s TG Prefill 4.224 · TTFT 2.350 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 14 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 314,04 tok/s TG Prefill 7.502 · TTFT 4.050 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 15 | North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 312,72 tok/s TG Prefill 4.146 · TTFT 5.378 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 16 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 310,59 tok/s TG Prefill 4.175 · TTFT 2.376 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 17 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 305,38 tok/s TG Prefill 5.073 · TTFT 5.334 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 18 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 303,14 tok/s TG Prefill 7.263 · TTFT 4.140 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 301,64 tok/s TG Prefill 7.030 · TTFT 4.327 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 20 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 300,93 tok/s TG Prefill 6.663 · TTFT 4.522 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 21 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 242,44 tok/s TG Prefill 3.921 · TTFT 5.712 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 22 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 237,33 tok/s TG Prefill 4.217 · TTFT 5.319 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 23 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 230,12 tok/s TG Prefill 5.654 · TTFT 2.560 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 24 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 228,11 tok/s TG Prefill 5.935 · TTFT 2.341 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 25 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 226,98 tok/s TG Prefill 3.204 · TTFT 3.127 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 226,87 tok/s TG Prefill 3.972 · TTFT 7.112 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 224,25 tok/s TG Prefill 3.178 · TTFT 3.153 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 223,82 tok/s TG Prefill 3.920 · TTFT 3.793 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 220,46 tok/s TG Prefill 5.841 · TTFT 2.373 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 220,09 tok/s TG Prefill 4.004 · TTFT 7.026 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 31 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 218,94 tok/s TG Prefill 5.830 · TTFT 2.480 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 32 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 216,88 tok/s TG Prefill 3.836 · TTFT 3.241 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 213,50 tok/s TG Prefill 5.805 · TTFT 2.392 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 213,37 tok/s TG Prefill 3.510 · TTFT 2.952 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 212,89 tok/s TG Prefill 638 · TTFT 31.124 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 212,06 tok/s TG Prefill 5.466 · TTFT 2.536 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 209,09 tok/s TG Prefill 646 · TTFT 30.756 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 38 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 207,68 tok/s TG Prefill 2.458 · TTFT 4.035 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,58 tok/s TG Prefill 3.095 · TTFT 3.242 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 186,86 tok/s TG Prefill 3.200 · TTFT 3.133 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 41 | Muse-Glimmer-30B30BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 182,69 tok/s TG Prefill 1.099 · TTFT 18.308 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 155,02 tok/s TG Prefill 2.329 · TTFT 12.088 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 154,86 tok/s TG Prefill 3.730 · TTFT 530 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 44 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 153,79 tok/s TG Prefill 2.885 · TTFT 4.280 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 45 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 151,50 tok/s TG Prefill 3.183 · TTFT 10.690 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 46 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 150,51 tok/s TG Prefill 3.701 · TTFT 533 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 47 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 145,54 tok/s TG Prefill 2.918 · TTFT 4.227 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 48 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 140,99 tok/s TG Prefill 1.453 · TTFT 6.814 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 49 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 135,10 tok/s TG Prefill 1.505 · TTFT 6.576 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 50 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 133,22 tok/s TG Prefill 5.127 · TTFT 390 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 51 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 117,25 tok/s TG Prefill 3.430 · TTFT 710 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 52 | Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 114,95 tok/s TG Prefill 3.401 · TTFT 715 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 53 | Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 114,69 tok/s TG Prefill 3.417 · TTFT 713 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 112,90 tok/s TG Prefill 3.054 · TTFT 797 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 55 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 112,54 tok/s TG Prefill 5.735 · TTFT 345 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 56 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 109,98 tok/s TG Prefill 1.323 · TTFT 17.042 ms | 10× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 57 | North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 109,84 tok/s TG Prefill 2.765 · TTFT 716 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 58 | Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 109,52 tok/s TG Prefill 3.194 · TTFT 762 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 59 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,60 tok/s TG Prefill 3.037 · TTFT 811 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 60 | Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 104,95 tok/s TG Prefill 3.020 · TTFT 909 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 61 | Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 101,60 tok/s TG Prefill 1.687 · TTFT 7.279 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 62 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 99,04 tok/s TG Prefill 2.389 · TTFT 6.000 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 63 | Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 95,19 tok/s TG Prefill 2.412 · TTFT 804 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 64 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 94,59 tok/s TG Prefill 2.458 · TTFT 786 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 65 | Muse-Glimmer-30B30BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 90,08 tok/s TG Prefill 978 · TTFT 10.061 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 66 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,33 tok/s TG Prefill 2.389 · TTFT 808 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 67 | Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,20 tok/s TG Prefill 2.622 · TTFT 754 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 68 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 80,98 tok/s TG Prefill 3.303 · TTFT 746 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 69 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,99 tok/s TG Prefill 997 · TTFT 10.047 ms | 5× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 70 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,09 tok/s TG Prefill 2.637 · TTFT 732 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 71 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,54 tok/s TG Prefill 2.060 · TTFT 1.099 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 72 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,19 tok/s TG Prefill 1.906 · TTFT 1.189 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 73 | Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,82 tok/s TG Prefill 1.231 · TTFT 1.830 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 74 | Mistral-Small-3.1-24B-Instruct-250324BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,65 tok/s TG Prefill 1.245 · TTFT 1.845 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 75 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,04 tok/s TG Prefill 1.508 · TTFT 1.312 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 76 | Muse-Glimmer-30B30BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,33 tok/s TG Prefill 927 · TTFT 2.113 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 77 | Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,83 tok/s TG Prefill 841 · TTFT 2.294 ms | 1× | Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → |