🏆
Rankings
LLM Leaderboard
Real measurements of every tested language model on real, named hardware – rated by raw speed (performance in tokens per second, prefill and time to first token) and by practical task quality in complete agent and chat runs (harness). Pick a benchmark type below or filter by model, maker and hardware to see exactly what is tested and how the results are produced.
⚡ Performance (tok/s)🤖 Harness quality👥 Concurrency🖥️ real hardware
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 641,39 tok/s TG Prefill 6.716 · TTFT 15.676 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 2 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 629,49 tok/s TG Prefill 6.861 · TTFT 15.390 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 559,41 tok/s TG Prefill 9.986 · TTFT 16.664 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 → | |
| 4 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 547,92 tok/s TG Prefill 8.153 · TTFT 16.930 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 → | |
| 5 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 455,34 tok/s TG Prefill 5.365 · TTFT 21.481 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 → | |
| 6 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 350,14 tok/s TG Prefill 6.541 · TTFT 4.589 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 7 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 346,65 tok/s TG Prefill 6.719 · TTFT 4.938 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 8 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 325,20 tok/s TG Prefill 3.507 · TTFT 31.980 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 9 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 306,90 tok/s TG Prefill 10.683 · TTFT 4.930 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 → | |
| 10 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 301,60 tok/s TG Prefill 6.192 · TTFT 5.565 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 → | |
| 11 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 277,86 tok/s TG Prefill 3.781 · TTFT 10.183 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | vLLMvllmAWQ | Details → | |
| 12 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 258,32 tok/s TG Prefill 5.049 · TTFT 6.208 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 → | |
| 13 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 214,10 tok/s TG Prefill 4.633 · TTFT 8.462 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | llamacpp | Details → | |
| 14 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 201,46 tok/s TG Prefill 3.877 · TTFT 48.219 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 15 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,80 tok/s TG Prefill 5.019 · TTFT 46.235 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 16 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 187,04 tok/s TG Prefill 4.177 · TTFT 15.498 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 17 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 184,33 tok/s TG Prefill 2.857 · TTFT 5.676 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | vLLMvllmAWQ | Details → | |
| 18 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 182,92 tok/s TG Prefill 4.049 · TTFT 17.792 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 181,91 tok/s TG Prefill 2.336 · TTFT 55.212 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 20 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 181,88 tok/s TG Prefill 4.310 · TTFT 15.943 ms | 10× | 2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 21 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 180,91 tok/s TG Prefill 4.113 · TTFT 19.821 ms | 10× | 2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 22 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 178,38 tok/s TG Prefill 3.257 · TTFT 10.368 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 23 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 169,10 tok/s TG Prefill 2.088 · TTFT 14.428 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 24 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 147,45 tok/s TG Prefill 1.813 · TTFT 17.552 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawIQ4_XS | Details → | |
| 25 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 134,52 tok/s TG Prefill 1.360 · TTFT 24.430 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 133,11 tok/s TG Prefill 1.768 · TTFT 18.406 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 27 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 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 → | |
| 28 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 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 → | |
| 29 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 125,21 tok/s TG Prefill 3.410 · TTFT 4.809 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | llamacpp | Details → | |
| 30 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 123,66 tok/s TG Prefill 2.453 · TTFT 6.575 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawIQ4_XS | Details → | |
| 31 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 123,33 tok/s TG Prefill 1.762 · TTFT 18.471 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 32 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 111,50 tok/s TG Prefill 1.387 · TTFT 11.441 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 110,27 tok/s TG Prefill 3.206 · TTFT 4.680 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 107,89 tok/s TG Prefill 3.707 · TTFT 13.889 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 107,79 tok/s TG Prefill 2.159 · TTFT 13.896 ms | 10× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 36 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 107,69 tok/s TG Prefill 4.844 · TTFT 12.709 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 107,24 tok/s TG Prefill 3.566 · TTFT 4.706 ms | 5× | 2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,55 tok/s TG Prefill 2.042 · TTFT 15.214 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 102,38 tok/s TG Prefill 1.243 · TTFT 27.006 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 40 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 101,58 tok/s TG Prefill 2.196 · TTFT 16.679 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 96,24 tok/s TG Prefill 4.036 · TTFT 673 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 42 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 94,15 tok/s TG Prefill 3.697 · TTFT 735 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 92,09 tok/s TG Prefill 2.810 · TTFT 6.013 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 44 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,16 tok/s TG Prefill 5.077 · TTFT 543 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 → | |
| 45 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,03 tok/s TG Prefill 4.755 · TTFT 577 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 → | |
| 46 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,63 tok/s TG Prefill 1.851 · TTFT 8.111 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 47 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 84,31 tok/s TG Prefill 2.202 · TTFT 7.548 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 48 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 81,08 tok/s TG Prefill 2.880 · TTFT 951 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 → | |
| 49 | Codestral-22B-v0.122BMistral AI Performance benchmark | 80,00 tok/s TG Prefill 1.200 · TTFT 150 ms | 8× | NVIDIA GB10 (DGX Spark)AMD Ryzen 9 9950X 16-Core Processor · 128 GB RAM | vLLMvllm | Details → | |
| 50 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 79,07 tok/s TG Prefill 3.492 · TTFT 4.570 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 51 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 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 → | |
| 52 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,13 tok/s TG Prefill 3.562 · TTFT 4.610 ms | 5× | 2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 53 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 75,70 tok/s TG Prefill 2.480 · TTFT 6.056 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 75,59 tok/s TG Prefill 1.180 · TTFT 12.748 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 55 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,35 tok/s TG Prefill 2.444 · TTFT 6.039 ms | 5× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 56 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,88 tok/s TG Prefill 1.114 · TTFT 148.957 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 57 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 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 → | |
| 58 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 57,55 tok/s TG Prefill 1.941 · TTFT 1.402 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | llamacpp | Details → | |
| 59 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 57,45 tok/s TG Prefill 1.958 · TTFT 1.391 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 60 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 45,38 tok/s TG Prefill 1.437 · TTFT 1.875 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAM | vllm | Details → | |
| 61 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 45,20 tok/s TG Prefill 886 · TTFT 3.072 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 62 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,74 tok/s TG Prefill 1.399 · TTFT 1.944 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawIQ4_XS | Details → | |
| 63 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,54 tok/s TG Prefill 1.774 · TTFT 1.537 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 64 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,46 tok/s TG Prefill 1.769 · TTFT 1.542 ms | 1× | 2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 65 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,80 tok/s TG Prefill 1.733 · TTFT 1.574 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 66 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 37,75 tok/s TG Prefill 1.478 · TTFT 1.835 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 67 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 34,87 tok/s TG Prefill 1.172 · TTFT 41.913 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 68 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,47 tok/s TG Prefill 810 · TTFT 3.810 ms | 1× | 3x AMD Radeon AI PRO R9700 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 69 | Codestral-22B-v0.122BMistral AI Performance benchmark | 33,47 tok/s TG Prefill 810 · TTFT 3.810 ms | 1× | 3x AMD Radeon AI PRO R9700 i32x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 70 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,21 tok/s TG Prefill 1.329 · TTFT 2.051 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 71 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 33,14 tok/s TG Prefill 2.208 · TTFT 1.231 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 72 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,94 tok/s TG Prefill 2.803 · TTFT 969 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 73 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 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 → | |
| 74 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 28,18 tok/s TG Prefill 791 · TTFT 3.443 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 75 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,75 tok/s TG Prefill 1.266 · TTFT 2.148 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 76 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,69 tok/s TG Prefill 1.241 · TTFT 2.193 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 77 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,68 tok/s TG Prefill 1.289 · TTFT 3.106 ms | 1× | 3x AMD Radeon AI PRO R9700 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 78 | Codestral-22B-v0.122BMistral AI Performance benchmark | 27,68 tok/s TG Prefill 1.289 · TTFT 3.106 ms | 1× | 3x AMD Radeon AI PRO R9700 i32x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 79 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 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 → | |
| 80 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,31 tok/s TG Prefill 1.876 · TTFT 1.453 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 81 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 27,30 tok/s TG Prefill 1.859 · TTFT 1.467 ms | 1× | 2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 82 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,47 tok/s TG Prefill 1.170 · TTFT 2.158 ms | 1× | 3x AMD Radeon AI PRO R9700 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 83 | Codestral-22B-v0.122BMistral AI Performance benchmark | 25,47 tok/s TG Prefill 1.170 · TTFT 2.158 ms | 1× | 3x AMD Radeon AI PRO R9700 i32x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 84 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,95 tok/s TG Prefill 1.821 · TTFT 1.498 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 85 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,64 tok/s TG Prefill 281 · TTFT 6.718 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 86 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,18 tok/s TG Prefill 319 · TTFT 8.542 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 61 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 87 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,24 tok/s TG Prefill 263 · TTFT 57.267 ms | 5× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 88 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 13,51 tok/s TG Prefill 185 · TTFT 14.723 ms | 1× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 89 | Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,98 tok/s TG Prefill 695 · TTFT 3.957 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → |