⚡
Performance benchmark
How fast is the model?
Raw throughput on real hardware – how many tokens a model generates per second, how quickly it processes the prompt and how short the time to first token is. Higher is better.
⚡ Generation (tok/s)🔄 Prefill⏱️ TTFT👥 Concurrency
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 901,86 tok/s TG Prefill 12.965 · TTFT 12.663 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 2 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 883,71 tok/s TG Prefill 12.981 · TTFT 12.917 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 3 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 797,18 tok/s TG Prefill 11.820 · TTFT 1.789 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 4 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 796,82 tok/s TG Prefill 11.892 · TTFT 1.781 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 5 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 670,65 tok/s TG Prefill 17.357 · TTFT 3.808 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 6 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 7 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 496,79 tok/s TG Prefill 12.291 · TTFT 3.700 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 8 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 487,24 tok/s TG Prefill 12.271 · TTFT 3.758 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 9 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 483,69 tok/s TG Prefill 9.270 · TTFT 1.070 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 10 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 479,47 tok/s TG Prefill 9.242 · TTFT 1.075 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 11 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 475,79 tok/s TG Prefill 6.572 · TTFT 3.089 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 12 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 475,57 tok/s TG Prefill 6.613 · TTFT 3.068 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 13 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 475,30 tok/s TG Prefill 5.812 · TTFT 1.707 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 14 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 475,27 tok/s TG Prefill 5.800 · TTFT 1.710 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 15 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 475,00 tok/s TG Prefill 6.609 · TTFT 3.072 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 16 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 474,73 tok/s TG Prefill 6.600 · TTFT 3.079 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 17 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 473,98 tok/s TG Prefill 6.595 · TTFT 3.077 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 18 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 473,82 tok/s TG Prefill 6.434 · TTFT 3.151 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 19 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 473,19 tok/s TG Prefill 6.576 · TTFT 3.084 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 20 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,98 tok/s TG Prefill 6.576 · TTFT 3.088 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 21 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,92 tok/s TG Prefill 6.577 · TTFT 3.088 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD 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) | 472,71 tok/s TG Prefill 6.385 · TTFT 3.174 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 23 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,68 tok/s TG Prefill 6.583 · TTFT 3.083 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 24 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,64 tok/s TG Prefill 6.577 · TTFT 3.084 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 25 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,60 tok/s TG Prefill 6.592 · TTFT 3.075 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 26 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,56 tok/s TG Prefill 6.399 · TTFT 3.168 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 27 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,49 tok/s TG Prefill 6.605 · TTFT 3.073 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 28 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,43 tok/s TG Prefill 6.543 · TTFT 3.103 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 29 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 30 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,98 tok/s TG Prefill 6.570 · TTFT 3.090 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 31 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,78 tok/s TG Prefill 6.446 · TTFT 3.147 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 32 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,61 tok/s TG Prefill 6.627 · TTFT 3.065 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 33 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,34 tok/s TG Prefill 6.588 · TTFT 3.081 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 34 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,33 tok/s TG Prefill 6.562 · TTFT 3.094 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 35 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,28 tok/s TG Prefill 6.424 · TTFT 3.156 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 36 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,13 tok/s TG Prefill 6.578 · TTFT 3.087 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 37 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,05 tok/s TG Prefill 6.622 · TTFT 3.068 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 38 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 471,04 tok/s TG Prefill 6.575 · TTFT 3.091 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 39 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 470,76 tok/s TG Prefill 6.586 · TTFT 3.084 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 40 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 470,37 tok/s TG Prefill 6.608 · TTFT 3.073 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 41 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 470,21 tok/s TG Prefill 6.615 · TTFT 3.070 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 42 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 470,17 tok/s TG Prefill 6.563 · TTFT 3.093 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 43 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,97 tok/s TG Prefill 6.570 · TTFT 3.091 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 44 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,85 tok/s TG Prefill 6.585 · TTFT 3.083 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 45 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,71 tok/s TG Prefill 6.608 · TTFT 3.074 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 46 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,66 tok/s TG Prefill 6.577 · TTFT 3.088 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 47 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,48 tok/s TG Prefill 6.637 · TTFT 3.060 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 48 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,28 tok/s TG Prefill 6.551 · TTFT 3.099 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 49 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,17 tok/s TG Prefill 6.594 · TTFT 3.080 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 50 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,04 tok/s TG Prefill 6.560 · TTFT 3.097 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 51 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 469,00 tok/s TG Prefill 6.592 · TTFT 3.081 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 52 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,75 tok/s TG Prefill 6.561 · TTFT 3.092 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 53 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,74 tok/s TG Prefill 6.617 · TTFT 3.069 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 54 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 55 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,55 tok/s TG Prefill 6.408 · TTFT 3.163 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 56 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,50 tok/s TG Prefill 6.586 · TTFT 3.084 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 57 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,28 tok/s TG Prefill 6.578 · TTFT 3.088 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 58 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,11 tok/s TG Prefill 6.601 · TTFT 3.076 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 59 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 467,60 tok/s TG Prefill 6.583 · TTFT 3.085 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 60 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 467,27 tok/s TG Prefill 6.597 · TTFT 3.078 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 61 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 467,25 tok/s TG Prefill 5.842 · TTFT 1.697 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 62 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,81 tok/s TG Prefill 6.592 · TTFT 3.077 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 63 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,68 tok/s TG Prefill 6.574 · TTFT 3.087 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 64 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,43 tok/s TG Prefill 6.563 · TTFT 3.094 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 65 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 66 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,20 tok/s TG Prefill 6.545 · TTFT 3.103 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 67 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,08 tok/s TG Prefill 5.852 · TTFT 1.695 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 68 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 69 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 70 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 465,47 tok/s TG Prefill 6.034 · TTFT 1.639 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 71 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 465,11 tok/s TG Prefill 5.888 · TTFT 1.687 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 72 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,82 tok/s TG Prefill 5.915 · TTFT 1.680 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 73 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,66 tok/s TG Prefill 5.853 · TTFT 1.697 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 74 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,61 tok/s TG Prefill 5.872 · TTFT 1.691 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 75 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,60 tok/s TG Prefill 5.893 · TTFT 1.685 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 76 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,49 tok/s TG Prefill 5.883 · TTFT 1.687 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 77 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,40 tok/s TG Prefill 5.886 · TTFT 1.688 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 78 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 79 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,09 tok/s TG Prefill 5.846 · TTFT 1.696 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 80 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,00 tok/s TG Prefill 5.830 · TTFT 1.703 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 81 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,98 tok/s TG Prefill 5.865 · TTFT 1.693 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 82 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,88 tok/s TG Prefill 5.828 · TTFT 1.704 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 83 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,88 tok/s TG Prefill 5.880 · TTFT 1.691 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 84 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,80 tok/s TG Prefill 5.895 · TTFT 1.684 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 85 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,78 tok/s TG Prefill 5.851 · TTFT 1.697 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 86 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,76 tok/s TG Prefill 5.845 · TTFT 1.697 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 87 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,67 tok/s TG Prefill 5.822 · TTFT 1.705 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 88 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,50 tok/s TG Prefill 5.867 · TTFT 1.694 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 89 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,44 tok/s TG Prefill 5.844 · TTFT 1.698 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 90 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,37 tok/s TG Prefill 5.882 · TTFT 1.688 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 91 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,29 tok/s TG Prefill 5.862 · TTFT 1.694 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 92 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,29 tok/s TG Prefill 5.816 · TTFT 1.707 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 93 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,13 tok/s TG Prefill 5.880 · TTFT 1.691 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 94 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,07 tok/s TG Prefill 5.857 · TTFT 1.696 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 95 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,05 tok/s TG Prefill 5.889 · TTFT 1.686 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 96 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,00 tok/s TG Prefill 5.849 · TTFT 1.697 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 97 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,92 tok/s TG Prefill 5.882 · TTFT 1.688 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 98 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,64 tok/s TG Prefill 5.864 · TTFT 1.692 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 99 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,62 tok/s TG Prefill 5.838 · TTFT 1.700 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 100 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,44 tok/s TG Prefill 5.918 · TTFT 1.680 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 101 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,17 tok/s TG Prefill 5.891 · TTFT 1.687 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 102 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,06 tok/s TG Prefill 5.826 · TTFT 1.702 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 103 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 461,82 tok/s TG Prefill 5.854 · TTFT 1.696 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 104 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 461,50 tok/s TG Prefill 5.864 · TTFT 1.693 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 105 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 461,14 tok/s TG Prefill 5.867 · TTFT 1.692 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 106 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 461,04 tok/s TG Prefill 5.868 · TTFT 1.692 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 107 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 460,58 tok/s TG Prefill 5.866 · TTFT 1.692 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 108 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 460,36 tok/s TG Prefill 5.864 · TTFT 1.693 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 109 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 460,05 tok/s TG Prefill 5.868 · TTFT 1.692 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 110 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 459,38 tok/s TG Prefill 5.875 · TTFT 1.690 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 111 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 459,37 tok/s TG Prefill 5.866 · TTFT 1.693 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 112 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 113 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 458,88 tok/s TG Prefill 5.872 · TTFT 1.692 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 114 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 457,83 tok/s TG Prefill 5.889 · TTFT 1.687 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 115 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 457,00 tok/s TG Prefill 5.877 · TTFT 1.691 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 116 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 403,67 tok/s TG Prefill 5.727 · TTFT 1.727 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 117 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 399,08 tok/s TG Prefill 14.492 · TTFT 984 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 118 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 119 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 330,94 tok/s TG Prefill 4.379 · TTFT 7.353 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 120 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,61 tok/s TG Prefill 5.586 · TTFT 354 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 121 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,55 tok/s TG Prefill 5.574 · TTFT 355 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 122 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,53 tok/s TG Prefill 5.527 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 123 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,51 tok/s TG Prefill 5.584 · TTFT 354 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 124 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,48 tok/s TG Prefill 5.521 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 125 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,47 tok/s TG Prefill 5.561 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 126 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,45 tok/s TG Prefill 5.512 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 127 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 128 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,38 tok/s TG Prefill 5.533 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 129 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,36 tok/s TG Prefill 5.532 · TTFT 357 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 130 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,35 tok/s TG Prefill 5.558 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 131 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,26 tok/s TG Prefill 5.522 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 132 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,18 tok/s TG Prefill 5.555 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 133 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,12 tok/s TG Prefill 5.569 · TTFT 355 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 134 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,10 tok/s TG Prefill 5.518 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 135 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,06 tok/s TG Prefill 5.285 · TTFT 374 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 136 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,01 tok/s TG Prefill 5.585 · TTFT 354 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 137 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,95 tok/s TG Prefill 5.518 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 138 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,92 tok/s TG Prefill 5.506 · TTFT 359 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 139 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 140 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,88 tok/s TG Prefill 5.524 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 141 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,88 tok/s TG Prefill 5.565 · TTFT 355 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 142 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,86 tok/s TG Prefill 5.555 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 143 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,85 tok/s TG Prefill 5.565 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 144 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,83 tok/s TG Prefill 5.544 · TTFT 357 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 145 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,82 tok/s TG Prefill 5.525 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 146 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,80 tok/s TG Prefill 5.584 · TTFT 354 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 147 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,78 tok/s TG Prefill 5.514 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 148 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,77 tok/s TG Prefill 5.542 · TTFT 357 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 149 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 150 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,69 tok/s TG Prefill 5.503 · TTFT 359 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 151 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,63 tok/s TG Prefill 5.520 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 152 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,63 tok/s TG Prefill 5.536 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 153 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,58 tok/s TG Prefill 5.520 · TTFT 359 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 154 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,52 tok/s TG Prefill 5.502 · TTFT 360 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 155 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,41 tok/s TG Prefill 5.566 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 156 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,39 tok/s TG Prefill 5.514 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 157 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,39 tok/s TG Prefill 5.508 · TTFT 360 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 158 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,34 tok/s TG Prefill 5.569 · TTFT 355 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 159 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,29 tok/s TG Prefill 5.550 · TTFT 356 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 160 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 245,24 tok/s TG Prefill 5.475 · TTFT 361 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 161 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 162 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,97 tok/s TG Prefill 5.542 · TTFT 357 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 163 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,96 tok/s TG Prefill 5.524 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 164 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,91 tok/s TG Prefill 5.575 · TTFT 355 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 165 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,81 tok/s TG Prefill 5.503 · TTFT 359 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 166 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,74 tok/s TG Prefill 5.548 · TTFT 357 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 167 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,74 tok/s TG Prefill 5.519 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 168 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,69 tok/s TG Prefill 5.512 · TTFT 359 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 169 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,64 tok/s TG Prefill 5.542 · TTFT 357 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 170 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,61 tok/s TG Prefill 5.521 · TTFT 358 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 171 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,44 tok/s TG Prefill 5.544 · TTFT 357 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 172 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,31 tok/s TG Prefill 5.561 · TTFT 355 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 173 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 244,26 tok/s TG Prefill 5.502 · TTFT 359 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 174 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 226,20 tok/s TG Prefill 2.929 · TTFT 4.189 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 175 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 176,18 tok/s TG Prefill 8.074 · TTFT 245 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 176 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 176,06 tok/s TG Prefill 7.970 · TTFT 248 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 177 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 171,72 tok/s TG Prefill 7.637 · TTFT 319 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 178 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,65 tok/s TG Prefill 7.081 · TTFT 345 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 179 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,59 tok/s TG Prefill 6.991 · TTFT 350 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 180 | 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 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 181 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,03 tok/s TG Prefill 1.644 · TTFT 1.302 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocketAWQ | Details → | |
| 182 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,73 tok/s TG Prefill 888 · TTFT 25.625 ms | 10× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 183 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,98 tok/s TG Prefill 642 · TTFT 15.446 ms | 5× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → | |
| 184 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,66 tok/s TG Prefill 533 · TTFT 3.719 ms | 1× | NVIDIA GeForce RTX 3090 Ti32x AMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | vLLMwebsocket | Details → |