🏆
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 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.015,69 tok/s TG Prefill 20.061 · TTFT 1.289 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 2 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 3 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 4 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 5 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 6 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 7 | 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 5090AMD 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) | 731,45 tok/s TG Prefill 14.635 · TTFT 1.415 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 9 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 615,82 tok/s TG Prefill 13.999 · TTFT 797 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 10 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 11 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 524,37 tok/s TG Prefill 7.751 · TTFT 4.130 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 12 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 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 → | |
| 13 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 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 → | |
| 14 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,71 tok/s TG Prefill 6.385 · TTFT 3.174 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 15 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,07 tok/s TG Prefill 6.589 · TTFT 3.082 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 16 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,63 tok/s TG Prefill 6.589 · TTFT 3.082 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 17 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,39 tok/s TG Prefill 6.589 · TTFT 3.082 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 18 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,05 tok/s TG Prefill 5.832 · TTFT 1.702 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 19 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 465,84 tok/s TG Prefill 5.890 · TTFT 1.687 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 20 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,36 tok/s TG Prefill 5.894 · TTFT 1.686 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 21 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 459,17 tok/s TG Prefill 5.840 · TTFT 1.699 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 22 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 23 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 24 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 25 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 338,30 tok/s TG Prefill 5.943 · TTFT 2.299 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 26 | 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 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 27 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 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 → | |
| 28 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 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 → | |
| 29 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,44 tok/s TG Prefill 5.547 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 30 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,90 tok/s TG Prefill 5.498 · TTFT 360 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 31 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,71 tok/s TG Prefill 5.516 · TTFT 359 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 32 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,24 tok/s TG Prefill 5.518 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 33 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 144,83 tok/s TG Prefill 9.895 · TTFT 217 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 34 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 131,17 tok/s TG Prefill 3.478 · TTFT 3.246 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 122,01 tok/s TG Prefill 4.646 · TTFT 5.658 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,07 tok/s TG Prefill 3.093 · TTFT 6.580 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,99 tok/s TG Prefill 3.266 · TTFT 6.177 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,92 tok/s TG Prefill 3.287 · TTFT 6.131 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,86 tok/s TG Prefill 3.241 · TTFT 6.213 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,62 tok/s TG Prefill 2.949 · TTFT 726 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 41 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,99 tok/s TG Prefill 3.127 · TTFT 6.476 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,59 tok/s TG Prefill 3.330 · TTFT 6.063 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 85,48 tok/s TG Prefill 1.228 · TTFT 16.535 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 44 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 85,15 tok/s TG Prefill 3.218 · TTFT 666 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 45 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 85,15 tok/s TG Prefill 3.218 · TTFT 666 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 46 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 84,44 tok/s TG Prefill 1.233 · TTFT 16.472 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 47 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 83,15 tok/s TG Prefill 1.230 · TTFT 16.507 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 48 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 80,50 tok/s TG Prefill 1.115 · TTFT 8.923 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 49 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,31 tok/s TG Prefill 1.110 · TTFT 8.951 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 50 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,10 tok/s TG Prefill 1.235 · TTFT 16.434 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 51 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 75,57 tok/s TG Prefill 1.120 · TTFT 8.896 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 52 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,06 tok/s TG Prefill 1.134 · TTFT 8.760 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 53 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 66,26 tok/s TG Prefill 1.512 · TTFT 17.280 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,13 tok/s TG Prefill 2.839 · TTFT 3.486 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 55 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,02 tok/s TG Prefill 2.824 · TTFT 3.507 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 56 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 56,83 tok/s TG Prefill 1.123 · TTFT 10.037 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 57 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 55,31 tok/s TG Prefill 3.034 · TTFT 6.676 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 58 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 55,26 tok/s TG Prefill 3.131 · TTFT 6.476 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 59 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 51,00 tok/s TG Prefill 3.205 · TTFT 716 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 60 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 50,36 tok/s TG Prefill 3.889 · TTFT 593 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 61 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,60 tok/s TG Prefill 1.097 · TTFT 1.804 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 62 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,60 tok/s TG Prefill 1.110 · TTFT 1.781 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 63 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,59 tok/s TG Prefill 2.183 · TTFT 1.016 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 64 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,51 tok/s TG Prefill 1.116 · TTFT 1.773 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 65 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,42 tok/s TG Prefill 2.700 · TTFT 3.669 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 66 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 46,27 tok/s TG Prefill 1.057 · TTFT 1.869 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 67 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 45,80 tok/s TG Prefill 2.725 · TTFT 3.630 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 68 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 39,81 tok/s TG Prefill 2.474 · TTFT 4.007 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 69 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,37 tok/s TG Prefill 2.661 · TTFT 3.726 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 70 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,34 tok/s TG Prefill 2.092 · TTFT 4.742 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 71 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,70 tok/s TG Prefill 2.460 · TTFT 4.043 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 72 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 24,83 tok/s TG Prefill 734 · TTFT 2.764 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 73 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,42 tok/s TG Prefill 1.652 · TTFT 1.198 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 74 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,34 tok/s TG Prefill 1.669 · TTFT 1.184 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 75 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,34 tok/s TG Prefill 1.805 · TTFT 1.094 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 76 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,34 tok/s TG Prefill 947 · TTFT 2.085 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 77 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,34 tok/s TG Prefill 1.772 · TTFT 1.114 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 78 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,33 tok/s TG Prefill 1.828 · TTFT 1.080 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 79 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,06 tok/s TG Prefill 948 · TTFT 2.099 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 80 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,34 tok/s TG Prefill 1.228 · TTFT 1.921 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → |