Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Performance-Benchmark

Wie schnell ist das Modell?

Roher Durchsatz auf echter Hardware – wie viele Token ein Modell pro Sekunde erzeugt, wie schnell es den Prompt verarbeitet und wie kurz die Zeit bis zum ersten Token ausfällt. Je höher, desto besser.

⚡ Generation (tok/s)🔄 Prefill⏱️ TTFT👥 Concurrency
Reset
Messwert:
Größe
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.608,46 tok/s TG
Prefill 31.452 · TTFT 1.633 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclaw
2gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.567,98 tok/s TG
Prefill 55.260 · TTFT 492 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
3Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.485,14 tok/s TG
Prefill 44.171 · TTFT 717 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
4gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.443,88 tok/s TG
Prefill 35.348 · TTFT 560 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclaw
5gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.386,79 tok/s TG
Prefill 19.981 · TTFT 1.205 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cli
6gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.359,09 tok/s TG
Prefill 47.158 · TTFT 587 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
7gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.295,30 tok/s TG
Prefill 25.462 · TTFT 808 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQ
8gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.238,26 tok/s TG
Prefill 21.843 · TTFT 905 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMvLLMgodclaw
9gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.122,50 tok/s TG
Prefill 38.712 · TTFT 690 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
10Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.070,56 tok/s TG
Prefill 33.741 · TTFT 976 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
11Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.062,52 tok/s TG
Prefill 21.965 · TTFT 1.226 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
12Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.028,59 tok/s TG
Prefill 24.461 · TTFT 1.670 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
13Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.028,53 tok/s TG
Prefill 36.884 · TTFT 916 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
14Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.026,44 tok/s TG
Prefill 26.805 · TTFT 1.371 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
15gemma-4-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.022,79 tok/s TG
Prefill 18.744 · TTFT 2.204 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclaw
16Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
1.015,69 tok/s TG
Prefill 20.061 · TTFT 1.289 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
17gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
973,54 tok/s TG
Prefill 23.599 · TTFT 460 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclaw
18Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
966,21 tok/s TG
Prefill 33.768 · TTFT 1.793 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQ
19Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
961,53 tok/s TG
Prefill 32.305 · TTFT 1.633 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
20Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
952,78 tok/s TG
Prefill 20.106 · TTFT 1.542 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
21Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
910,74 tok/s TG
Prefill 33.907 · TTFT 1.527 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
22Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
909,25 tok/s TG
Prefill 37.116 · TTFT 1.783 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQ
23gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
909,00 tok/s TG
Prefill 43.093 · TTFT 288 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
24Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
906,04 tok/s TG
Prefill 39.029 · TTFT 1.193 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
25Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
901,86 tok/s TG
Prefill 12.965 · TTFT 12.663 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocketAWQ
26Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
899,41 tok/s TG
Prefill 30.214 · TTFT 473 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
27Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
883,71 tok/s TG
Prefill 12.981 · TTFT 12.917 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocketAWQ
28Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
881,75 tok/s TG
Prefill 22.565 · TTFT 1.184 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
29Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
873,72 tok/s TG
Prefill 33.023 · TTFT 1.835 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQ
30gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
842,94 tok/s TG
Prefill 31.098 · TTFT 319 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclaw
31Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
841,75 tok/s TG
Prefill 32.027 · TTFT 923 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
32Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
836,37 tok/s TG
Prefill 39.157 · TTFT 1.033 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
33Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
832,96 tok/s TG
Prefill 27.508 · TTFT 1.327 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
34gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
803,96 tok/s TG
Prefill 16.236 · TTFT 616 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cli
35gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
803,18 tok/s TG
Prefill 35.757 · TTFT 347 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
36Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
800,39 tok/s TG
Prefill 32.313 · TTFT 827 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
37Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
799,65 tok/s TG
Prefill 31.954 · TTFT 834 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
38gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
797,18 tok/s TG
Prefill 11.820 · TTFT 1.789 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocket
39gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
796,82 tok/s TG
Prefill 11.892 · TTFT 1.781 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocket
40Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
791,54 tok/s TG
Prefill 26.710 · TTFT 1.226 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
41gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
790,09 tok/s TG
Prefill 13.693 · TTFT 1.142 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMvLLMgodclaw
42Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
789,24 tok/s TG
Prefill 37.676 · TTFT 952 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
43Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
787,25 tok/s TG
Prefill 32.522 · TTFT 826 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
44Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
786,19 tok/s TG
Prefill 19.249 · TTFT 1.376 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
45gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
784,45 tok/s TG
Prefill 17.724 · TTFT 560 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQ
46Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
771,80 tok/s TG
Prefill 34.194 · TTFT 1.184 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
47Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
763,50 tok/s TG
Prefill 35.900 · TTFT 987 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
48Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
758,69 tok/s TG
Prefill 34.913 · TTFT 992 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
49Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
754,69 tok/s TG
Prefill 26.306 · TTFT 1.120 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
50Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
751,67 tok/s TG
Prefill 32.340 · TTFT 1.271 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
51Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
735,14 tok/s TG
Prefill 16.886 · TTFT 1.945 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
52Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
732,27 tok/s TG
Prefill 28.221 · TTFT 955 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
53Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
729,28 tok/s TG
Prefill 27.628 · TTFT 966 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
54Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
726,94 tok/s TG
Prefill 10.204 · TTFT 2.619 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
55Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
725,58 tok/s TG
Prefill 11.872 · TTFT 2.430 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
56Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
720,92 tok/s TG
Prefill 30.926 · TTFT 1.138 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
57Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
718,47 tok/s TG
Prefill 28.493 · TTFT 951 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
58Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
712,04 tok/s TG
Prefill 35.143 · TTFT 1.137 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
59Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
697,04 tok/s TG
Prefill 30.227 · TTFT 1.164 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
60Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
691,32 tok/s TG
Prefill 30.805 · TTFT 1.147 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
61Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
690,88 tok/s TG
Prefill 29.513 · TTFT 1.000 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
62gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
681,82 tok/s TG
Prefill 16.224 · TTFT 1.899 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
63Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
676,76 tok/s TG
Prefill 21.675 · TTFT 725 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
64Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
675,29 tok/s TG
Prefill 20.479 · TTFT 781 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
65Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
673,19 tok/s TG
Prefill 30.512 · TTFT 1.156 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
66Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
670,65 tok/s TG
Prefill 17.357 · TTFT 3.808 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocketAWQ
67Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
666,52 tok/s TG
Prefill 27.804 · TTFT 465 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
68Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
664,59 tok/s TG
Prefill 27.704 · TTFT 965 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
69Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
658,68 tok/s TG
Prefill 27.910 · TTFT 964 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
70Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
655,83 tok/s TG
Prefill 17.990 · TTFT 931 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQ
71Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
655,42 tok/s TG
Prefill 30.671 · TTFT 1.283 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
72Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
655,08 tok/s TG
Prefill 14.863 · TTFT 2.211 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
73Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
649,04 tok/s TG
Prefill 17.868 · TTFT 764 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
74North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
648,52 tok/s TG
Prefill 29.491 · TTFT 1.310 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
75Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
647,82 tok/s TG
Prefill 16.265 · TTFT 725 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
76Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
633,41 tok/s TG
Prefill 20.292 · TTFT 767 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cliAWQ
77gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
631,69 tok/s TG
Prefill 29.259 · TTFT 405 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
78Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
630,94 tok/s TG
Prefill 24.767 · TTFT 1.191 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
79Qwen3-Coder-NextQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
629,83 tok/s TG
Prefill 26.016 · TTFT 1.347 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
80Ornith-1.5-35B-A3B35BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
626,41 tok/s TG
Prefill 28.681 · TTFT 928 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
81Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
625,71 tok/s TG
Prefill 31.724 · TTFT 396 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
82Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
622,29 tok/s TG
Prefill 24.690 · TTFT 1.093 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
83Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
618,22 tok/s TG
Prefill 28.790 · TTFT 435 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
84gemma-4-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
616,01 tok/s TG
Prefill 13.778 · TTFT 803 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclaw
85Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
615,82 tok/s TG
Prefill 13.999 · TTFT 797 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
86Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
611,40 tok/s TG
Prefill 11.799 · TTFT 2.083 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
87gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
610,99 tok/s TG
Prefill 14.285 · TTFT 2.134 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
88Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
610,90 tok/s TG
Prefill 25.129 · TTFT 1.087 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
89North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
598,90 tok/s TG
Prefill 30.083 · TTFT 948 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
90Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
596,47 tok/s TG
Prefill 26.540 · TTFT 369 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
91Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
594,77 tok/s TG
Prefill 25.604 · TTFT 404 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
92Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
592,35 tok/s TG
Prefill 20.010 · TTFT 1.519 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
93Ornith-1.5-35B-A3B35BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
588,56 tok/s TG
Prefill 25.569 · TTFT 1.053 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
94Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
588,46 tok/s TG
Prefill 20.028 · TTFT 1.512 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
95Qwen3-Coder-NextQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
587,94 tok/s TG
Prefill 22.877 · TTFT 1.531 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
96Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
582,71 tok/s TG
Prefill 31.647 · TTFT 1.123 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
97Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
580,46 tok/s TG
Prefill 29.873 · TTFT 587 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
98Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
576,78 tok/s TG
Prefill 14.305 · TTFT 2.330 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
99Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
573,56 tok/s TG
Prefill 31.043 · TTFT 1.133 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
100gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
572,10 tok/s TG
Prefill 10.901 · TTFT 1.915 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMvLLMvllm mxfp4
101gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
561,51 tok/s TG
Prefill 16.822 · TTFT 1.831 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
102Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
554,20 tok/s TG
Prefill 31.733 · TTFT 1.123 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
103Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
551,23 tok/s TG
Prefill 24.679 · TTFT 522 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
104Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
547,72 tok/s TG
Prefill 30.727 · TTFT 1.142 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
105Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
544,78 tok/s TG
Prefill 26.473 · TTFT 1.278 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
106Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
544,17 tok/s TG
Prefill 28.427 · TTFT 547 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
107Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
536,72 tok/s TG
Prefill 9.810 · TTFT 3.224 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
108Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
536,31 tok/s TG
Prefill 26.577 · TTFT 575 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
109Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
534,84 tok/s TG
Prefill 10.455 · TTFT 3.204 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
110Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
533,54 tok/s TG
Prefill 16.604 · TTFT 5.626 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawBF16
111Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
529,82 tok/s TG
Prefill 27.634 · TTFT 1.287 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
112Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
526,99 tok/s TG
Prefill 19.777 · TTFT 1.490 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
113Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
525,52 tok/s TG
Prefill 25.936 · TTFT 678 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
114Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
524,37 tok/s TG
Prefill 7.751 · TTFT 4.130 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocketAWQ
115Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
521,64 tok/s TG
Prefill 18.046 · TTFT 1.070 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
116North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
518,08 tok/s TG
Prefill 33.281 · TTFT 870 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
117Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
516,37 tok/s TG
Prefill 27.317 · TTFT 1.298 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
118Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
515,26 tok/s TG
Prefill 31.910 · TTFT 1.107 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
119Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
515,25 tok/s TG
Prefill 27.809 · TTFT 1.285 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
120Qwen3-Coder-NextQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
514,52 tok/s TG
Prefill 22.477 · TTFT 1.541 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
121gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
513,46 tok/s TG
Prefill 15.021 · TTFT 2.056 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
122Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
512,98 tok/s TG
Prefill 24.564 · TTFT 483 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
123Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
510,34 tok/s TG
Prefill 6.104 · TTFT 4.473 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
124Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
510,30 tok/s TG
Prefill 21.461 · TTFT 752 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
125Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
508,01 tok/s TG
Prefill 28.153 · TTFT 552 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
126Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
507,66 tok/s TG
Prefill 17.126 · TTFT 696 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
127Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
505,62 tok/s TG
Prefill 24.212 · TTFT 484 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
128Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
504,76 tok/s TG
Prefill 24.274 · TTFT 484 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
129Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
500,57 tok/s TG
Prefill 5.466 · TTFT 5.230 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
130Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
497,64 tok/s TG
Prefill 8.340 · TTFT 5.360 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawAWQ
131Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
496,79 tok/s TG
Prefill 12.291 · TTFT 3.700 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocketAWQ
132Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
492,95 tok/s TG
Prefill 9.614 · TTFT 3.459 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
133Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
492,58 tok/s TG
Prefill 9.647 · TTFT 3.456 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
134Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
492,12 tok/s TG
Prefill 20.612 · TTFT 628 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
135North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
489,20 tok/s TG
Prefill 28.361 · TTFT 1.013 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
136Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
488,90 tok/s TG
Prefill 21.158 · TTFT 1.413 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
137Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
488,87 tok/s TG
Prefill 23.837 · TTFT 1.604 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
138Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
487,24 tok/s TG
Prefill 12.271 · TTFT 3.758 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocketAWQ
139Qwen3-Coder-NextQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
487,01 tok/s TG
Prefill 20.068 · TTFT 1.732 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
140gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
486,20 tok/s TG
Prefill 4.345 · TTFT 5.863 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclaw
141Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
484,47 tok/s TG
Prefill 27.552 · TTFT 1.279 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
142Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
484,10 tok/s TG
Prefill 23.812 · TTFT 655 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
143gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
483,69 tok/s TG
Prefill 9.270 · TTFT 1.070 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocket
144gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
479,47 tok/s TG
Prefill 9.242 · TTFT 1.075 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocket
145Nemotron-3-Nano-4B4BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
478,23 tok/s TG
Prefill 20.306 · TTFT 679 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
146Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
470,21 tok/s TG
Prefill 23.352 · TTFT 1.410 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
147Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
469,89 tok/s TG
Prefill 23.294 · TTFT 668 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
148North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
467,57 tok/s TG
Prefill 27.350 · TTFT 464 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
149Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
466,27 tok/s TG
Prefill 13.248 · TTFT 1.078 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
150Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
464,18 tok/s TG
Prefill 12.655 · TTFT 1.950 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
151Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
463,86 tok/s TG
Prefill 20.910 · TTFT 563 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
152Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
462,53 tok/s TG
Prefill 14.492 · TTFT 817 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
153Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
462,23 tok/s TG
Prefill 24.899 · TTFT 645 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
154Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
460,32 tok/s TG
Prefill 20.972 · TTFT 563 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
155Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
459,96 tok/s TG
Prefill 23.681 · TTFT 660 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
156Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
455,02 tok/s TG
Prefill 20.984 · TTFT 561 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
157Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
453,61 tok/s TG
Prefill 21.156 · TTFT 557 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
158Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
451,89 tok/s TG
Prefill 23.930 · TTFT 658 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
159gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
451,05 tok/s TG
Prefill 32.005 · TTFT 864 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMvLLMvllm
160Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
450,20 tok/s TG
Prefill 21.244 · TTFT 558 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
161Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
447,47 tok/s TG
Prefill 22.711 · TTFT 564 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
162Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
446,80 tok/s TG
Prefill 18.959 · TTFT 1.330 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
163Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
444,58 tok/s TG
Prefill 15.076 · TTFT 2.208 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
164Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
444,25 tok/s TG
Prefill 18.777 · TTFT 1.343 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
165Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
442,56 tok/s TG
Prefill 18.820 · TTFT 1.340 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
166Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
440,04 tok/s TG
Prefill 22.431 · TTFT 1.470 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
167Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
439,35 tok/s TG
Prefill 22.619 · TTFT 1.445 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
168gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
437,98 tok/s TG
Prefill 12.559 · TTFT 1.057 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
169Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
431,74 tok/s TG
Prefill 7.853 · TTFT 3.851 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
170North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
431,36 tok/s TG
Prefill 23.725 · TTFT 543 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
171Qwen3.8-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
426,54 tok/s TG
Prefill 7.926 · TTFT 3.884 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
172Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
423,35 tok/s TG
Prefill 6.026 · TTFT 2.001 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
173Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
423,25 tok/s TG
Prefill 11.522 · TTFT 1.241 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
174Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
419,82 tok/s TG
Prefill 18.271 · TTFT 644 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
175Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
419,41 tok/s TG
Prefill 14.676 · TTFT 885 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
176Ornith-1.5-35B-A3B35BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
418,21 tok/s TG
Prefill 21.951 · TTFT 535 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
177Qwen3.5-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
417,28 tok/s TG
Prefill 18.311 · TTFT 646 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
178Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
415,85 tok/s TG
Prefill 22.897 · TTFT 1.440 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
179Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
415,29 tok/s TG
Prefill 14.768 · TTFT 886 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
180Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
411,83 tok/s TG
Prefill 7.172 · TTFT 1.728 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
181Qwen3-Coder-NextQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
410,37 tok/s TG
Prefill 19.698 · TTFT 777 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
182Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
409,55 tok/s TG
Prefill 23.648 · TTFT 741 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
183Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
408,21 tok/s TG
Prefill 19.748 · TTFT 657 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
184Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
404,55 tok/s TG
Prefill 24.684 · TTFT 634 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
185Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
401,40 tok/s TG
Prefill 9.462 · TTFT 3.339 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
186Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
399,08 tok/s TG
Prefill 14.492 · TTFT 984 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocketAWQ
187gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
398,25 tok/s TG
Prefill 11.255 · TTFT 1.183 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
188Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
397,81 tok/s TG
Prefill 11.797 · TTFT 1.550 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawBF16
189Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
394,94 tok/s TG
Prefill 21.192 · TTFT 1.768 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
190Devstral-Small-250724BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
394,57 tok/s TG
Prefill 11.196 · TTFT 3.006 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
191Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
393,62 tok/s TG
Prefill 20.483 · TTFT 1.464 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
192Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
393,13 tok/s TG
Prefill 24.244 · TTFT 640 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
193Ornith-1.5-35B-A3B35BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
391,05 tok/s TG
Prefill 19.044 · TTFT 619 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
194Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
387,59 tok/s TG
Prefill 10.645 · TTFT 1.347 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
195Qwen3.6-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
387,30 tok/s TG
Prefill 7.115 · TTFT 4.230 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
196Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
386,05 tok/s TG
Prefill 23.773 · TTFT 648 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
197Qwen3.8-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
383,33 tok/s TG
Prefill 7.228 · TTFT 4.259 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
198gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
383,05 tok/s TG
Prefill 9.509 · TTFT 3.275 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
199Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
381,56 tok/s TG
Prefill 24.720 · TTFT 634 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
200Qwen3-Coder-NextQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
378,00 tok/s TG
Prefill 17.176 · TTFT 892 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
201Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
377,91 tok/s TG
Prefill 19.202 · TTFT 1.574 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
202gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
372,40 tok/s TG
Prefill 1.508 · TTFT 13.832 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMvLLMllamacppAWQ
203Devstral-Small-250724BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
371,52 tok/s TG
Prefill 10.318 · TTFT 3.250 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
204Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
368,97 tok/s TG
Prefill 21.359 · TTFT 736 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
205Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
368,20 tok/s TG
Prefill 8.707 · TTFT 1.231 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
206Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
367,00 tok/s TG
Prefill 24.948 · TTFT 625 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
207North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
366,96 tok/s TG
Prefill 25.394 · TTFT 501 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
208Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
365,67 tok/s TG
Prefill 21.449 · TTFT 1.461 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
209Qwen3-Coder-NextQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
365,08 tok/s TG
Prefill 17.147 · TTFT 895 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
210Laguna-XS-2.1Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
364,01 tok/s TG
Prefill 18.353 · TTFT 886 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
211Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
362,62 tok/s TG
Prefill 7.057 · TTFT 5.416 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
212Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
362,62 tok/s TG
Prefill 7.178 · TTFT 5.398 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
213Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
361,95 tok/s TG
Prefill 20.414 · TTFT 748 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
214Nemotron-3-Nano-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
361,45 tok/s TG
Prefill 21.222 · TTFT 1.462 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
215Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
357,72 tok/s TG
Prefill 20.957 · TTFT 747 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
216North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
356,91 tok/s TG
Prefill 23.191 · TTFT 1.190 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
217Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
356,42 tok/s TG
Prefill 16.357 · TTFT 2.480 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
218Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
349,19 tok/s TG
Prefill 6.664 · TTFT 5.253 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
219Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
348,36 tok/s TG
Prefill 21.278 · TTFT 737 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
220Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
348,18 tok/s TG
Prefill 14.665 · TTFT 859 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
221gemma-4-E4B-it8BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
346,29 tok/s TG
Prefill 16.028 · TTFT 1.776 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMvLLMvllm bf16
222Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
344,15 tok/s TG
Prefill 15.326 · TTFT 2.709 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
223Qwen3-Coder-NextQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
342,54 tok/s TG
Prefill 15.132 · TTFT 1.011 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
224North-Mini-Code-1.0Cohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
340,09 tok/s TG
Prefill 21.845 · TTFT 589 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
225gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
338,81 tok/s TG
Prefill 13.627 · TTFT 983 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
226Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
338,30 tok/s TG
Prefill 5.943 · TTFT 2.299 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocketAWQ
227Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
332,90 tok/s TG
Prefill 21.275 · TTFT 732 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
228Qwen2.5-Coder-32B-Instruct32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
332,31 tok/s TG
Prefill 6.040 · TTFT 5.832 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
229Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
332,07 tok/s TG
Prefill 6.084 · TTFT 5.812 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
230Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
330,94 tok/s TG
Prefill 4.379 · TTFT 7.353 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMvLLMwebsocketAWQ
231Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
330,53 tok/s TG
Prefill 17.325 · TTFT 814 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
232Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
329,05 tok/s TG
Prefill 8.161 · TTFT 1.778 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
233Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
327,23 tok/s TG
Prefill 8.158 · TTFT 1.764 ms
5×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
234Nemotron-Cascade-2-30B-A3B30BNVIDIA PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
326,85 tok/s TG
Prefill 125 · TTFT 210.255 ms
5×AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAMvLLMgodclawBF16
235Gemma-4-26B-A4B-it26BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
321,71 tok/s TG
Prefill 16.555 · TTFT 787 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
236Seed-OSS-36B-Instruct36BByteDance Seed PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
321,35 tok/s TG
Prefill 6.209 · TTFT 5.624 ms
10×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
237Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
319,74 tok/s TG
Prefill 19.044 · TTFT 1.730 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
238Qwen3.8-27B27BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
319,01 tok/s TG
Prefill 7.048 · TTFT 4.342 ms
10×2x NVIDIA RTX A6000 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
239Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
318,66 tok/s TG
Prefill 5.742 · TTFT 2.122 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclawAWQ
240Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
315,88 tok/s TG
Prefill 16.870 · TTFT 841 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
241Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
315,74 tok/s TG
Prefill 17.208 · TTFT 823 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliAWQ
242gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
315,66 tok/s TG
Prefill 3.728 · TTFT 2.722 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMvLLMgodclaw
243gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
314,80 tok/s TG
Prefill 11.946 · TTFT 1.124 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawFP8
244gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
308,36 tok/s TG
Prefill 9.336 · TTFT 1.062 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMvLLMvllm mxfp4
245gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
306,80 tok/s TG
Prefill 9.358 · TTFT 1.060 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMvLLMvllm mxfp4
246Devstral-Small-2-24B-Instruct-251224BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
306,77 tok/s TG
Prefill 7.576 · TTFT 1.901 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
247Magistral-Small-250924BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
306,07 tok/s TG
Prefill 7.668 · TTFT 1.898 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
248Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
300,61 tok/s TG
Prefill 4.931 · TTFT 2.537 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMvLLMgodclawAWQ
249gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
300,27 tok/s TG
Prefill 10.207 · TTFT 3.065 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
250Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
300,16 tok/s TG
Prefill 19.050 · TTFT 1.732 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8