🏆
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 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.307,85 tok/s TG Prefill 12.817 · TTFT 1.998 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 2 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 976,74 tok/s TG Prefill 10.282 · TTFT 1.672 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 3 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 958,87 tok/s TG Prefill 8.733 · TTFT 2.404 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 4 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 945,36 tok/s TG Prefill 10.586 · TTFT 1.034 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 5 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 924,77 tok/s TG Prefill 14.070 · TTFT 1.518 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 6 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 900,87 tok/s TG Prefill 14.222 · TTFT 1.494 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 7 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 883,09 tok/s TG Prefill 11.941 · TTFT 846 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 8 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 862,91 tok/s TG Prefill 11.878 · TTFT 884 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 9 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 860,24 tok/s TG Prefill 11.718 · TTFT 850 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 10 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 859,80 tok/s TG Prefill 10.736 · TTFT 922 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 11 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 854,00 tok/s TG Prefill 11.767 · TTFT 917 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 12 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 850,49 tok/s TG Prefill 11.762 · TTFT 848 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 13 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 850,30 tok/s TG Prefill 14.558 · TTFT 681 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 14 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 849,72 tok/s TG Prefill 12.081 · TTFT 822 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 15 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 849,71 tok/s TG Prefill 13.306 · TTFT 742 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 16 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 849,26 tok/s TG Prefill 14.308 · TTFT 691 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 17 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 848,83 tok/s TG Prefill 14.662 · TTFT 679 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 18 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 848,28 tok/s TG Prefill 12.860 · TTFT 769 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 19 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 847,93 tok/s TG Prefill 13.048 · TTFT 758 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 20 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 847,91 tok/s TG Prefill 12.215 · TTFT 821 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 21 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 847,27 tok/s TG Prefill 14.549 · TTFT 681 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 22 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 847,15 tok/s TG Prefill 14.371 · TTFT 689 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 23 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 846,47 tok/s TG Prefill 14.593 · TTFT 679 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 24 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 846,22 tok/s TG Prefill 13.031 · TTFT 758 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 25 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 846,00 tok/s TG Prefill 15.052 · TTFT 658 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 26 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 845,94 tok/s TG Prefill 12.772 · TTFT 775 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 27 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 845,91 tok/s TG Prefill 14.817 · TTFT 667 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 28 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 844,91 tok/s TG Prefill 12.314 · TTFT 802 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 29 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 844,60 tok/s TG Prefill 14.970 · TTFT 661 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 30 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 843,77 tok/s TG Prefill 14.526 · TTFT 682 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 31 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 843,27 tok/s TG Prefill 12.338 · TTFT 808 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 32 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 843,15 tok/s TG Prefill 14.600 · TTFT 678 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 33 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 842,86 tok/s TG Prefill 13.574 · TTFT 735 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 34 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 842,72 tok/s TG Prefill 13.001 · TTFT 760 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 35 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 842,36 tok/s TG Prefill 14.985 · TTFT 660 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 36 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 841,72 tok/s TG Prefill 14.604 · TTFT 678 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 37 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 841,61 tok/s TG Prefill 14.924 · TTFT 662 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 38 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 840,86 tok/s TG Prefill 13.153 · TTFT 752 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 39 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 839,87 tok/s TG Prefill 14.692 · TTFT 673 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 40 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 839,65 tok/s TG Prefill 14.503 · TTFT 682 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 41 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 839,46 tok/s TG Prefill 12.054 · TTFT 829 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 42 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 837,07 tok/s TG Prefill 13.165 · TTFT 751 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 43 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 834,68 tok/s TG Prefill 14.205 · TTFT 697 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 44 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 834,30 tok/s TG Prefill 11.355 · TTFT 946 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 45 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 831,97 tok/s TG Prefill 12.715 · TTFT 778 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 46 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 830,73 tok/s TG Prefill 11.816 · TTFT 897 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 47 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 828,75 tok/s TG Prefill 11.025 · TTFT 899 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 48 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 828,31 tok/s TG Prefill 9.374 · TTFT 1.203 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 49 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 818,56 tok/s TG Prefill 10.674 · TTFT 1.064 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 50 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 808,63 tok/s TG Prefill 11.644 · TTFT 899 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 51 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 806,97 tok/s TG Prefill 13.113 · TTFT 753 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 52 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 794,89 tok/s TG Prefill 15.020 · TTFT 1.548 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 53 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 793,40 tok/s TG Prefill 12.941 · TTFT 821 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 54 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 792,43 tok/s TG Prefill 10.847 · TTFT 911 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 55 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 791,28 tok/s TG Prefill 14.004 · TTFT 1.508 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 56 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 787,90 tok/s TG Prefill 14.843 · TTFT 1.365 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 57 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 786,52 tok/s TG Prefill 14.441 · TTFT 1.612 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 58 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 780,52 tok/s TG Prefill 16.226 · TTFT 1.246 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 59 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 779,25 tok/s TG Prefill 18.661 · TTFT 1.138 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 60 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 777,90 tok/s TG Prefill 12.244 · TTFT 1.770 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 61 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 774,64 tok/s TG Prefill 15.560 · TTFT 1.306 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 62 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 774,46 tok/s TG Prefill 12.604 · TTFT 817 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 63 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 774,05 tok/s TG Prefill 14.584 · TTFT 1.392 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 64 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 773,21 tok/s TG Prefill 17.224 · TTFT 1.181 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 65 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 772,97 tok/s TG Prefill 15.485 · TTFT 1.305 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 66 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 772,94 tok/s TG Prefill 15.778 · TTFT 1.286 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 67 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 772,60 tok/s TG Prefill 16.608 · TTFT 1.217 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 68 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 772,44 tok/s TG Prefill 16.968 · TTFT 1.196 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 69 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 771,61 tok/s TG Prefill 16.052 · TTFT 1.260 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 70 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 771,41 tok/s TG Prefill 16.999 · TTFT 1.199 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 71 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 771,15 tok/s TG Prefill 14.854 · TTFT 1.362 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 72 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 770,56 tok/s TG Prefill 12.946 · TTFT 772 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 73 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 770,10 tok/s TG Prefill 17.225 · TTFT 1.181 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 74 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,96 tok/s TG Prefill 17.133 · TTFT 1.186 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 75 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,88 tok/s TG Prefill 17.307 · TTFT 1.172 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 76 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,69 tok/s TG Prefill 16.223 · TTFT 1.254 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 77 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,62 tok/s TG Prefill 8.231 · TTFT 2.166 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 78 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,56 tok/s TG Prefill 14.504 · TTFT 1.386 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 79 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,46 tok/s TG Prefill 17.541 · TTFT 1.168 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 80 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,38 tok/s TG Prefill 16.312 · TTFT 1.242 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 81 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,38 tok/s TG Prefill 17.501 · TTFT 1.163 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 82 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 769,19 tok/s TG Prefill 16.788 · TTFT 1.215 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 83 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 768,67 tok/s TG Prefill 17.616 · TTFT 1.162 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 84 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 768,27 tok/s TG Prefill 15.002 · TTFT 1.342 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 85 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 767,75 tok/s TG Prefill 17.100 · TTFT 1.190 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 86 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 767,74 tok/s TG Prefill 17.363 · TTFT 1.172 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 87 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 767,70 tok/s TG Prefill 17.221 · TTFT 1.181 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 88 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 767,52 tok/s TG Prefill 15.436 · TTFT 1.312 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 89 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 767,52 tok/s TG Prefill 14.994 · TTFT 1.351 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 90 | Magistral-Small-2509Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 766,82 tok/s TG Prefill 17.315 · TTFT 1.171 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 91 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 766,02 tok/s TG Prefill 16.992 · TTFT 1.204 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 92 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 765,41 tok/s TG Prefill 15.737 · TTFT 1.366 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 93 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 765,35 tok/s TG Prefill 15.325 · TTFT 1.319 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 94 | Qwen3-30B-A3B-Instruct-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 765,34 tok/s TG Prefill 16.138 · TTFT 1.260 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 95 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 763,58 tok/s TG Prefill 14.721 · TTFT 1.432 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 96 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 762,63 tok/s TG Prefill 17.216 · TTFT 1.180 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 97 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 762,49 tok/s TG Prefill 17.165 · TTFT 1.182 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 98 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 761,70 tok/s TG Prefill 16.271 · TTFT 1.470 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 99 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 761,43 tok/s TG Prefill 16.543 · TTFT 1.234 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 100 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 760,06 tok/s TG Prefill 14.581 · TTFT 1.398 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 101 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 759,81 tok/s TG Prefill 16.068 · TTFT 1.263 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 102 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 759,11 tok/s TG Prefill 15.793 · TTFT 1.289 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 103 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 759,06 tok/s TG Prefill 17.416 · TTFT 1.170 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 104 | Qwen3-30B-A3B-Thinking-2507Qwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 758,27 tok/s TG Prefill 16.769 · TTFT 1.237 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 105 | Qwen3-Coder-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 756,70 tok/s TG Prefill 13.710 · TTFT 728 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 106 | Codestral-22B-v0.1Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 755,27 tok/s TG Prefill 14.787 · TTFT 1.384 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 107 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 752,00 tok/s TG Prefill 15.899 · TTFT 1.273 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 108 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 749,99 tok/s TG Prefill 15.882 · TTFT 1.380 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 109 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 743,70 tok/s TG Prefill 14.753 · TTFT 1.375 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 110 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 738,23 tok/s TG Prefill 16.007 · TTFT 1.336 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 111 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 737,89 tok/s TG Prefill 15.880 · TTFT 1.271 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 112 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 731,45 tok/s TG Prefill 14.635 · TTFT 1.415 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 113 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 728,96 tok/s TG Prefill 10.917 · TTFT 977 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 114 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 728,62 tok/s TG Prefill 12.837 · TTFT 1.673 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 115 | Qwen2.5-Coder-32B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 722,59 tok/s TG Prefill 15.154 · TTFT 1.334 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 116 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 710,19 tok/s TG Prefill 12.056 · TTFT 841 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 117 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 697,75 tok/s TG Prefill 15.409 · TTFT 1.307 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 118 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 677,14 tok/s TG Prefill 16.172 · TTFT 1.355 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 119 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 669,44 tok/s TG Prefill 11.783 · TTFT 840 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 120 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 656,59 tok/s TG Prefill 10.521 · TTFT 978 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 121 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 609,63 tok/s TG Prefill 11.935 · TTFT 914 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 122 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 607,98 tok/s TG Prefill 11.742 · TTFT 1.524 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 123 | Devstral-Small-2-24B-Instruct-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 559,10 tok/s TG Prefill 11.563 · TTFT 857 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 124 | Devstral-Small-2507Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 523,30 tok/s TG Prefill 12.414 · TTFT 840 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 125 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 126 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 127 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 128 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 129 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 130 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 131 | 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 TiAMD 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) | 473,82 tok/s TG Prefill 6.434 · TTFT 3.151 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 133 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 134 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 135 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 136 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,71 tok/s TG Prefill 6.385 · TTFT 3.174 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 137 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 138 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 139 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 140 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 141 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 142 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 143 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 472,07 tok/s TG Prefill 6.589 · TTFT 3.082 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 144 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 145 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 146 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 147 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 148 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 149 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 150 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 151 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 152 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 153 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 154 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 155 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 156 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 157 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 158 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 159 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 160 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 161 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 162 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 163 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 164 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 165 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 166 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 167 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 168 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,63 tok/s TG Prefill 6.589 · TTFT 3.082 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 169 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 170 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 171 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,36 tok/s TG Prefill 6.574 · TTFT 3.085 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 172 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 173 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 468,13 tok/s TG Prefill 6.577 · TTFT 3.087 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 174 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 175 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 176 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 177 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 178 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,84 tok/s TG Prefill 6.428 · TTFT 3.155 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 179 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 180 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 181 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 182 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,39 tok/s TG Prefill 6.589 · TTFT 3.082 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 183 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,25 tok/s TG Prefill 6.602 · TTFT 3.077 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 184 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 185 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 186 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 466,05 tok/s TG Prefill 5.832 · TTFT 1.702 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 187 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 465,84 tok/s TG Prefill 5.890 · TTFT 1.687 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 188 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 465,64 tok/s TG Prefill 6.592 · TTFT 3.082 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 189 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 190 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 465,30 tok/s TG Prefill 6.571 · TTFT 3.092 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 191 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 192 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,86 tok/s TG Prefill 6.593 · TTFT 3.079 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 193 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,84 tok/s TG Prefill 5.865 · TTFT 1.694 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 194 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 195 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 196 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 197 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 198 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 199 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 200 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 464,36 tok/s TG Prefill 5.894 · TTFT 1.686 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 201 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 202 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 203 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 204 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 205 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 206 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 207 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,78 tok/s TG Prefill 6.600 · TTFT 3.078 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 208 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 209 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 210 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 211 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 212 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 213 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 214 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 215 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 216 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 217 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 218 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 219 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 220 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 221 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,91 tok/s TG Prefill 5.824 · TTFT 1.703 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 222 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,70 tok/s TG Prefill 5.893 · TTFT 1.686 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 223 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 224 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 225 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 226 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 227 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 228 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,02 tok/s TG Prefill 6.600 · TTFT 3.076 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 229 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 230 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 461,57 tok/s TG Prefill 5.941 · TTFT 1.667 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 231 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 232 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 233 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 234 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 460,78 tok/s TG Prefill 5.838 · TTFT 1.700 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 235 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 236 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 460,52 tok/s TG Prefill 5.827 · TTFT 1.703 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 237 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 238 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 239 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 240 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 241 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 459,17 tok/s TG Prefill 5.840 · TTFT 1.699 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 242 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 458,88 tok/s TG Prefill 5.851 · TTFT 1.697 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 243 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 244 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 245 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 457,75 tok/s TG Prefill 5.865 · TTFT 1.692 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 246 | 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 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 247 | gpt-oss-120bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 454,82 tok/s TG Prefill 6.007 · TTFT 1.649 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 248 | GLM-4.5-AirZ.ai (Zhipu) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 438,60 tok/s TG Prefill 6.700 · TTFT 296 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 249 | Mistral-Small-3.1-24B-Instruct-2503Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 432,51 tok/s TG Prefill 4.608 · TTFT 429 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 250 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 404,99 tok/s TG Prefill 9.572 · TTFT 208 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → |