🏆
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 | Devstral-Small-2-24B-Instruct-251224BAWQMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 725,58 tok/s TG Prefill 11.872 · TTFT 2.430 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 2 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 645,14 tok/s TG Prefill 10.717 · TTFT 14.083 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 3 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 620,27 tok/s TG Prefill 8.842 · TTFT 15.213 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 4 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 569,71 tok/s TG Prefill 13.325 · TTFT 16.210 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 5 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 560,66 tok/s TG Prefill 11.362 · TTFT 16.890 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 6 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 456,52 tok/s TG Prefill 7.113 · TTFT 20.834 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 7 | Devstral-Small-2-24B-Instruct-251224BAWQMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 423,35 tok/s TG Prefill 6.026 · TTFT 2.001 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 8 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 358,30 tok/s TG Prefill 8.069 · TTFT 4.298 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 9 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 340,40 tok/s TG Prefill 6.735 · TTFT 4.649 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 10 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 331,64 tok/s TG Prefill 4.743 · TTFT 31.297 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 11 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 303,65 tok/s TG Prefill 10.972 · TTFT 4.979 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 12 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 296,26 tok/s TG Prefill 9.510 · TTFT 4.914 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 13 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 247,69 tok/s TG Prefill 5.149 · TTFT 6.214 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | llamacpp | Details → | |
| 14 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,11 tok/s TG Prefill 6.585 · TTFT 5.543 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 15 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 206,34 tok/s TG Prefill 5.938 · TTFT 44.987 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 16 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 206,26 tok/s TG Prefill 4.766 · TTFT 42.744 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 17 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 199,08 tok/s TG Prefill 3.016 · TTFT 51.389 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 18 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 175,32 tok/s TG Prefill 3.605 · TTFT 9.714 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 19 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 152,07 tok/s TG Prefill 1.734 · TTFT 18.061 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 20 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 136,80 tok/s TG Prefill 3.720 · TTFT 8.188 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 21 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 131,37 tok/s TG Prefill 2.411 · TTFT 12.631 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 22 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 123,94 tok/s TG Prefill 3.957 · TTFT 3.439 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | llamacpp | Details → | |
| 23 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 118,31 tok/s TG Prefill 1.356 · TTFT 9.496 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 24 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 115,02 tok/s TG Prefill 1.562 · TTFT 20.338 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 25 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,78 tok/s TG Prefill 3.792 · TTFT 12.949 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 26 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,50 tok/s TG Prefill 2.121 · TTFT 85.480 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 27 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 108,16 tok/s TG Prefill 4.914 · TTFT 12.245 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 28 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 104,92 tok/s TG Prefill 2.267 · TTFT 15.348 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 29 | Devstral-Small-2-24B-Instruct-251224BAWQMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 96,87 tok/s TG Prefill 5.696 · TTFT 375 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 30 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 94,60 tok/s TG Prefill 3.347 · TTFT 833 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cli | Details → | |
| 31 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 94,49 tok/s TG Prefill 6.040 · TTFT 447 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclaw | Details → | |
| 32 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,59 tok/s TG Prefill 1.860 · TTFT 7.191 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 33 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,65 tok/s TG Prefill 4.998 · TTFT 541 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 34 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,64 tok/s TG Prefill 6.789 · TTFT 396 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 35 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI HarnessbenchmarkTool Usage Standard 1.0 | 2.597 Pkt 87,1% · 16/16 Aufg. · 165,0 s | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclaw | Details → | |
| 36 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 80,71 tok/s TG Prefill 3.360 · TTFT 806 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclaw | Details → | |
| 37 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,71 tok/s TG Prefill 2.812 · TTFT 4.702 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 38 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,21 tok/s TG Prefill 1.333 · TTFT 10.455 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 39 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI HarnessbenchmarkGodBrain MCP Deep 40 - Wissensbasis-Lebenszyklus 1.0 | 5.738 Pkt 75,7% · 40/40 Aufg. · 1.879,0 s | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclaw | Details → | |
| 40 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI HarnessbenchmarkTool Usage Extrem 40 - Tech-Radar Mission 1.0 | 5.629 Pkt 68,6% · 40/40 Aufg. · 2.018,0 s | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclaw | Details → | |
| 41 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,83 tok/s TG Prefill 1.470 · TTFT 24.544 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 42 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 56,18 tok/s TG Prefill 2.655 · TTFT 1.019 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocket | Details → | |
| 43 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,77 tok/s TG Prefill 822 · TTFT 2.606 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 44 | Devstral-Small-2-24B-Instruct-251224BIQ4_XSMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,28 tok/s TG Prefill 1.272 · TTFT 1.682 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 45 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,25 tok/s TG Prefill 1.534 · TTFT 1.394 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 46 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,61 tok/s TG Prefill 1.683 · TTFT 1.610 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 47 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,30 tok/s TG Prefill 2.713 · TTFT 996 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 48 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,93 tok/s TG Prefill 3.342 · TTFT 807 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 49 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 29,35 tok/s TG Prefill 905 · TTFT 3.213 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 50 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performancebenchmark i | 29,35 tok/s TG Prefill 905 · TTFT 3.213 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 51 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 28,62 tok/s TG Prefill 704 · TTFT 3.039 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 52 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 28,36 tok/s TG Prefill 1.176 · TTFT 1.820 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 53 | Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 28,27 tok/s TG Prefill 1.667 · TTFT 1.617 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 54 | Devstral-Small-2-24B-Instruct-251224BMistral AI Performancebenchmark i | 28,27 tok/s TG Prefill 1.667 · TTFT 1.617 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 55 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 28,24 tok/s TG Prefill 1.569 · TTFT 1.948 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 56 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI Performancebenchmark i | 28,24 tok/s TG Prefill 1.569 · TTFT 1.948 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 57 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI HarnessbenchmarkTool-Parcours Dossier 40 V1.0 | 1.436 Pkt 24,1% · 21/40 Aufg. · 8.887,0 s | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclaw | Details → | |
| 58 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,29 tok/s TG Prefill 273 · TTFT 55.104 ms | 5× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cli | Details → | |
| 59 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,15 tok/s TG Prefill 1.266 · TTFT 2.131 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 60 | Devstral-Small-2-24B-Instruct-251224BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 13,47 tok/s TG Prefill 197 · TTFT 13.734 ms | 1× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cli | Details → | |
| 61 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI PerformancebenchmarkPerformancetest Small 1.0 | 8,88 tok/s TG Prefill 22 · TTFT 906 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclaw | Details → | |
| 62 | Devstral-Small-2-24B-Instruct-251224BQ8_0Mistral AI Performancebenchmark | 8,88 tok/s TG Prefill 22 · TTFT 906 ms | 1× | AMD Radeon 8060S Graphics32x AMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | godclaw | Details → |