⚡
Performance-Benchmark
Wie schnell ist das Modell?
Roher Durchsatz auf echter Hardware – wie viele Token ein Modell pro Sekunde erzeugt, wie schnell es den Prompt verarbeitet und wie kurz die Zeit bis zum ersten Token ausfällt. Je höher, desto besser.
⚡ Generation (tok/s)🔄 Prefill⏱️ TTFT👥 Concurrency
| # | Modell / Hersteller | Messwerte | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.386,79 tok/s TG Prefill 19.981 · TTFT 1.205 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 2 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.295,30 tok/s TG Prefill 25.462 · TTFT 808 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 3 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 966,21 tok/s TG Prefill 33.768 · TTFT 1.793 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 4 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 945,36 tok/s TG Prefill 10.586 · TTFT 1.034 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 5 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 924,77 tok/s TG Prefill 14.070 · TTFT 1.518 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 6 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 909,25 tok/s TG Prefill 37.116 · TTFT 1.783 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 7 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 900,87 tok/s TG Prefill 14.222 · TTFT 1.494 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 8 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 883,09 tok/s TG Prefill 11.941 · TTFT 846 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 9 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 873,72 tok/s TG Prefill 33.023 · TTFT 1.835 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 10 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 860,24 tok/s TG Prefill 11.718 · TTFT 850 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 11 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 859,80 tok/s TG Prefill 10.736 · TTFT 922 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 12 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 848,28 tok/s TG Prefill 12.860 · TTFT 769 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 13 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 847,91 tok/s TG Prefill 12.215 · TTFT 821 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 14 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 831,97 tok/s TG Prefill 12.715 · TTFT 778 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 15 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 828,31 tok/s TG Prefill 9.374 · TTFT 1.203 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 16 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 818,56 tok/s TG Prefill 10.674 · TTFT 1.064 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 17 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 803,96 tok/s TG Prefill 16.236 · TTFT 616 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 18 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 793,40 tok/s TG Prefill 12.941 · TTFT 821 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 19 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 787,90 tok/s TG Prefill 14.843 · TTFT 1.365 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 20 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 786,52 tok/s TG Prefill 14.441 · TTFT 1.612 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 21 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 784,45 tok/s TG Prefill 17.724 · TTFT 560 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 22 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 771,61 tok/s TG Prefill 16.052 · TTFT 1.260 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 23 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,56 tok/s TG Prefill 14.504 · TTFT 1.386 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 24 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 763,58 tok/s TG Prefill 14.721 · TTFT 1.432 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 25 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 761,70 tok/s TG Prefill 16.271 · TTFT 1.470 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 26 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 759,06 tok/s TG Prefill 17.416 · TTFT 1.170 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 27 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 755,27 tok/s TG Prefill 14.787 · TTFT 1.384 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 28 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 749,99 tok/s TG Prefill 15.882 · TTFT 1.380 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 29 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 737,89 tok/s TG Prefill 15.880 · TTFT 1.271 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 30 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 731,45 tok/s TG Prefill 14.635 · TTFT 1.415 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 31 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 688,61 tok/s TG Prefill 16.192 · TTFT 873 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 32 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 677,14 tok/s TG Prefill 16.172 · TTFT 1.355 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 33 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 669,44 tok/s TG Prefill 11.783 · TTFT 840 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 34 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 656,59 tok/s TG Prefill 10.521 · TTFT 978 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 35 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 655,83 tok/s TG Prefill 17.990 · TTFT 931 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 36 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 633,41 tok/s TG Prefill 20.292 · TTFT 767 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 37 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 609,63 tok/s TG Prefill 11.935 · TTFT 914 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 38 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 559,10 tok/s TG Prefill 11.563 · TTFT 857 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 39 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 404,77 tok/s TG Prefill 6.150 · TTFT 340 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 40 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 404,59 tok/s TG Prefill 8.241 · TTFT 257 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 41 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 398,49 tok/s TG Prefill 6.929 · TTFT 317 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 42 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 397,99 tok/s TG Prefill 6.870 · TTFT 288 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 43 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 397,80 tok/s TG Prefill 5.599 · TTFT 359 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 44 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 395,32 tok/s TG Prefill 6.892 · TTFT 287 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 45 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 395,25 tok/s TG Prefill 7.545 · TTFT 262 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 46 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 388,85 tok/s TG Prefill 2.378 · TTFT 1.888 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 47 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 382,59 tok/s TG Prefill 3.167 · TTFT 747 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 48 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 379,03 tok/s TG Prefill 5.661 · TTFT 349 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 49 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 372,25 tok/s TG Prefill 6.985 · TTFT 284 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 50 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 368,12 tok/s TG Prefill 4.731 · TTFT 417 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 51 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 335,03 tok/s TG Prefill 3.379 · TTFT 604 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 52 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 333,50 tok/s TG Prefill 4.901 · TTFT 490 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 53 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 280,15 tok/s TG Prefill 9.224 · TTFT 217 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 54 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 267,04 tok/s TG Prefill 7.273 · TTFT 272 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 55 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 243,00 tok/s TG Prefill 4.297 · TTFT 765 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 56 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 232,79 tok/s TG Prefill 8.323 · TTFT 311 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 57 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 221,28 tok/s TG Prefill 8.379 · TTFT 300 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 58 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,31 tok/s TG Prefill 654 · TTFT 34.975 ms | 10× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 59 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 17,85 tok/s TG Prefill 481 · TTFT 21.081 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 60 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 13,32 tok/s TG Prefill 405 · TTFT 26.375 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 61 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,79 tok/s TG Prefill 406 · TTFT 4.916 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 62 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,46 tok/s TG Prefill 333 · TTFT 6.064 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 63 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,20 tok/s TG Prefill 382 · TTFT 35.625 ms | 5× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 64 | Mistral-Small-4-119B-2603Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,77 tok/s TG Prefill 325 · TTFT 5.900 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 65 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,34 tok/s TG Prefill 182 · TTFT 11.740 ms | 1× | NVIDIA GeForce RTX 509016x AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → |