Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
🏆
Rankings

LLM Leaderboard

Real measurements of every tested language model on real, named hardware – rated by raw speed (performance in tokens per second, prefill and time to first token) and by practical task quality in complete agent and chat runs (harness). Pick a benchmark type below or filter by model, maker and hardware to see exactly what is tested and how the results are produced.

⚡ Performance (tok/s)🤖 Harness quality👥 Concurrency🖥️ real hardware
Reset
Metric:
Size
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
667,02 tok/s TG
Prefill 4.019 · TTFT 17.735 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
2Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
655,34 tok/s TG
Prefill 4.936 · TTFT 17.123 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
3Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
629,37 tok/s TG
Prefill 4.530 · TTFT 17.991 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
4Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
518,27 tok/s TG
Prefill 13.775 · TTFT 18.702 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
5Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
508,08 tok/s TG
Prefill 5.204 · TTFT 21.109 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
6Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
489,43 tok/s TG
Prefill 10.618 · TTFT 18.898 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
7Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
487,60 tok/s TG
Prefill 5.077 · TTFT 20.649 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
8Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
476,21 tok/s TG
Prefill 5.858 · TTFT 20.719 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
9Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
474,97 tok/s TG
Prefill 3.481 · TTFT 22.488 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
10Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
382,25 tok/s TG
Prefill 3.656 · TTFT 5.903 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
11Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
375,87 tok/s TG
Prefill 4.619 · TTFT 5.434 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
12Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
358,48 tok/s TG
Prefill 4.148 · TTFT 5.814 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
13Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
329,89 tok/s TG
Prefill 5.097 · TTFT 30.395 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
14Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
327,48 tok/s TG
Prefill 6.307 · TTFT 30.045 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
15Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
325,23 tok/s TG
Prefill 3.265 · TTFT 32.856 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
16Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
290,27 tok/s TG
Prefill 35.719 · TTFT 1.015 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawBF16
17Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
286,24 tok/s TG
Prefill 2.858 · TTFT 1.792 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
18Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
281,80 tok/s TG
Prefill 10.273 · TTFT 5.323 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
19Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
277,95 tok/s TG
Prefill 8.575 · TTFT 597 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
20Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
275,72 tok/s TG
Prefill 13.406 · TTFT 4.952 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
21Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
274,94 tok/s TG
Prefill 6.188 · TTFT 6.209 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
22Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
273,62 tok/s TG
Prefill 5.151 · TTFT 994 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
23Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
271,41 tok/s TG
Prefill 8.886 · TTFT 576 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
24Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
271,41 tok/s TG
Prefill 8.886 · TTFT 0 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench
25Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
270,40 tok/s TG
Prefill 6.824 · TTFT 750 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
26Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
265,88 tok/s TG
Prefill 2.862 · TTFT 894 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
27Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
262,22 tok/s TG
Prefill 9.011 · TTFT 568 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmUD-Q4_K_M
28Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
261,45 tok/s TG
Prefill 4.824 · TTFT 6.145 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
29Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
260,59 tok/s TG
Prefill 6.954 · TTFT 368 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
30Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
256,65 tok/s TG
Prefill 4.749 · TTFT 539 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
31Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
255,30 tok/s TG
Prefill 5.644 · TTFT 6.016 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
32Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
254,56 tok/s TG
Prefill 3.174 · TTFT 7.205 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
33Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
253,13 tok/s TG
Prefill 5.903 · TTFT 434 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
34Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
247,13 tok/s TG
Prefill 9.886 · TTFT 518 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
35Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
244,04 tok/s TG
Prefill 5.934 · TTFT 863 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
36Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
241,82 tok/s TG
Prefill 7.918 · TTFT 647 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
37Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
232,53 tok/s TG
Prefill 7.614 · TTFT 336 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmUD-Q4_K_M
38Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
229,95 tok/s TG
Prefill 655 · TTFT 21.862 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
39Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
229,39 tok/s TG
Prefill 5.064 · TTFT 1.011 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
40Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
226,35 tok/s TG
Prefill 7.505 · TTFT 341 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
41Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
224,79 tok/s TG
Prefill 606 · TTFT 26.540 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
42Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
222,82 tok/s TG
Prefill 4.205 · TTFT 4.901 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
43Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
220,45 tok/s TG
Prefill 4.107 · TTFT 5.581 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
44Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
217,41 tok/s TG
Prefill 2.159 · TTFT 4.552 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
45Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
216,85 tok/s TG
Prefill 3.842 · TTFT 5.955 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
46Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
216,36 tok/s TG
Prefill 8.015 · TTFT 319 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
47Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
216,16 tok/s TG
Prefill 3.928 · TTFT 5.087 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
48Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
212,92 tok/s TG
Prefill 3.795 · TTFT 6.753 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
49Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
210,79 tok/s TG
Prefill 606 · TTFT 28.206 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
50Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
210,46 tok/s TG
Prefill 6.833 · TTFT 375 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
51Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
210,36 tok/s TG
Prefill 3.683 · TTFT 5.472 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
52Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
207,55 tok/s TG
Prefill 3.338 · TTFT 3.388 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
53Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
206,34 tok/s TG
Prefill 5.938 · TTFT 44.987 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
54Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
206,26 tok/s TG
Prefill 4.766 · TTFT 42.744 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
55Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
205,80 tok/s TG
Prefill 7.519 · TTFT 31.654 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
56Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
205,12 tok/s TG
Prefill 6.044 · TTFT 32.830 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
57Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
202,20 tok/s TG
Prefill 5.476 · TTFT 468 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
58Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
201,46 tok/s TG
Prefill 3.877 · TTFT 48.219 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
59Muse-Glimmer-30B30BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
199,09 tok/s TG
Prefill 2.520 · TTFT 2.032 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
60Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
199,08 tok/s TG
Prefill 3.016 · TTFT 51.389 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
61Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
198,80 tok/s TG
Prefill 5.019 · TTFT 46.235 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
62Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
192,69 tok/s TG
Prefill 3.898 · TTFT 37.605 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
63Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
192,66 tok/s TG
Prefill 2.706 · TTFT 3.642 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
64Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
192,16 tok/s TG
Prefill 2.755 · TTFT 3.564 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
65Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
192,04 tok/s TG
Prefill 3.084 · TTFT 2.806 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
66Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
189,98 tok/s TG
Prefill 4.071 · TTFT 5.658 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
67Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
188,35 tok/s TG
Prefill 4.100 · TTFT 5.611 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
68Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
187,06 tok/s TG
Prefill 2.824 · TTFT 3.499 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
69Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
186,28 tok/s TG
Prefill 3.569 · TTFT 2.478 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
70Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
185,39 tok/s TG
Prefill 3.957 · TTFT 2.535 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
71Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
183,45 tok/s TG
Prefill 4.012 · TTFT 2.498 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
72Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
181,99 tok/s TG
Prefill 3.958 · TTFT 2.533 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
73Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
181,97 tok/s TG
Prefill 3.848 · TTFT 5.198 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
74Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
181,91 tok/s TG
Prefill 2.336 · TTFT 55.212 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
75Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
181,74 tok/s TG
Prefill 3.527 · TTFT 2.492 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
76Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
181,28 tok/s TG
Prefill 3.620 · TTFT 2.799 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
77Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
181,01 tok/s TG
Prefill 3.865 · TTFT 5.849 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
78Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
178,15 tok/s TG
Prefill 3.106 · TTFT 7.058 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
79Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
173,97 tok/s TG
Prefill 3.522 · TTFT 2.513 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
80Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
173,24 tok/s TG
Prefill 4.852 · TTFT 8.741 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
81Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
171,87 tok/s TG
Prefill 3.023 · TTFT 10.146 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
82Ministral-3-14B-Reasoning-251214BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
171,59 tok/s TG
Prefill 6.061 · TTFT 8.390 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
83Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
170,48 tok/s TG
Prefill 23.477 · TTFT 582 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawBF16
84Qwen3.5-122B-A10B122BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
168,57 tok/s TG
Prefill 13.855 · TTFT 2.538 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawGPTQ
85Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
167,21 tok/s TG
Prefill 3.497 · TTFT 6.460 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
86Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
165,40 tok/s TG
Prefill 1.938 · TTFT 60.555 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
87Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
164,46 tok/s TG
Prefill 1.637 · TTFT 62.197 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
88gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
163,57 tok/s TG
Prefill 260 · TTFT 122.321 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
89gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
162,73 tok/s TG
Prefill 260 · TTFT 122.965 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
90gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
162,66 tok/s TG
Prefill 262 · TTFT 121.770 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
91Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
160,64 tok/s TG
Prefill 13.528 · TTFT 3.190 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
92Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
160,21 tok/s TG
Prefill 2.383 · TTFT 10.663 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
93Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
159,77 tok/s TG
Prefill 1.098 · TTFT 68.122 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
94Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
159,57 tok/s TG
Prefill 2.376 · TTFT 10.673 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliQ4_K_M
95Muse-Glimmer-30B30BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
159,55 tok/s TG
Prefill 3.112 · TTFT 1.645 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
96Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
154,95 tok/s TG
Prefill 3.643 · TTFT 6.292 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
97Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
154,26 tok/s TG
Prefill 10.264 · TTFT 3.946 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
98Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
153,33 tok/s TG
Prefill 23.508 · TTFT 1.417 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawBF16
99gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
147,82 tok/s TG
Prefill 3.534 · TTFT 555 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
100gpt-oss-20b20BOpenAI Performance benchmark
147,82 tok/s TG
Prefill 3.534 · TTFT 555 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
101Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
146,44 tok/s TG
Prefill 6.889 · TTFT 4.782 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ-INT4
102Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
144,27 tok/s TG
Prefill 5.193 · TTFT 493 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMopenclaw_cliFP8
103gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
143,90 tok/s TG
Prefill 4.229 · TTFT 464 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
104gpt-oss-20b20BOpenAI Performance benchmark
143,90 tok/s TG
Prefill 4.229 · TTFT 464 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
105Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
141,11 tok/s TG
Prefill 1.831 · TTFT 16.128 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
106Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
139,75 tok/s TG
Prefill 3.025 · TTFT 712 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
107gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
137,66 tok/s TG
Prefill 4.422 · TTFT 445 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
108gpt-oss-20b20BOpenAI Performance benchmark
137,66 tok/s TG
Prefill 4.422 · TTFT 445 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
109Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
136,24 tok/s TG
Prefill 3.620 · TTFT 595 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
110Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
131,42 tok/s TG
Prefill 2.111 · TTFT 5.856 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cliQ4_K_M
111Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
129,52 tok/s TG
Prefill 3.211 · TTFT 671 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
112Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
127,39 tok/s TG
Prefill 1.511 · TTFT 3.388 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
113Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
125,69 tok/s TG
Prefill 1.771 · TTFT 1.085 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
114Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
125,29 tok/s TG
Prefill 2.467 · TTFT 4.937 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
115Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
122,37 tok/s TG
Prefill 269 · TTFT 141.283 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
116Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
122,13 tok/s TG
Prefill 269 · TTFT 141.200 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
117Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
122,08 tok/s TG
Prefill 272 · TTFT 140.873 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
118Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
121,93 tok/s TG
Prefill 270 · TTFT 141.290 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
119Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
121,92 tok/s TG
Prefill 269 · TTFT 140.690 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
120Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
121,82 tok/s TG
Prefill 269 · TTFT 141.070 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
121Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
121,30 tok/s TG
Prefill 2.872 · TTFT 178 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
122Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
121,28 tok/s TG
Prefill 271 · TTFT 141.620 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
123Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
121,14 tok/s TG
Prefill 268 · TTFT 141.582 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
124Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
120,98 tok/s TG
Prefill 269 · TTFT 141.455 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
125Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
118,51 tok/s TG
Prefill 482 · TTFT 2.854 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
126Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
117,63 tok/s TG
Prefill 1.021 · TTFT 14.961 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
127Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
113,57 tok/s TG
Prefill 2.783 · TTFT 184 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
128Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
112,02 tok/s TG
Prefill 553 · TTFT 3.143 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
129Magistral-Small-250924BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
111,95 tok/s TG
Prefill 473 · TTFT 3.796 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
130Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
109,40 tok/s TG
Prefill 6.025 · TTFT 9.558 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
131Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
109,11 tok/s TG
Prefill 4.704 · TTFT 10.335 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
132Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
108,78 tok/s TG
Prefill 3.792 · TTFT 12.949 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
133Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
108,16 tok/s TG
Prefill 4.914 · TTFT 12.245 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
134Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
108,12 tok/s TG
Prefill 2.777 · TTFT 184 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
135Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
107,89 tok/s TG
Prefill 3.707 · TTFT 13.889 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
136Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
107,87 tok/s TG
Prefill 3.141 · TTFT 690 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
137Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
107,69 tok/s TG
Prefill 4.844 · TTFT 12.709 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
138Seed-OSS-36B-Instruct36BByteDance Seed Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
107,25 tok/s TG
Prefill 1.621 · TTFT 14.654 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
139gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
107,02 tok/s TG
Prefill 173 · TTFT 186.661 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
140Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
106,96 tok/s TG
Prefill 2.955 · TTFT 1.733 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
141gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
106,85 tok/s TG
Prefill 172 · TTFT 186.714 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
142Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
106,46 tok/s TG
Prefill 2.518 · TTFT 762 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
143Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
105,94 tok/s TG
Prefill 2.835 · TTFT 181 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
144Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
105,88 tok/s TG
Prefill 2.728 · TTFT 789 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
145gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
105,39 tok/s TG
Prefill 170 · TTFT 189.655 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
146Devstral-Small-2-24B-Instruct-251224BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
104,92 tok/s TG
Prefill 2.267 · TTFT 15.348 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
147Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
104,78 tok/s TG
Prefill 284 · TTFT 139.519 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
148Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
104,34 tok/s TG
Prefill 3.766 · TTFT 8.416 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ-INT4
149GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
104,08 tok/s TG
Prefill 2.674 · TTFT 8.272 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
150Devstral-Small-250724BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
103,69 tok/s TG
Prefill 2.847 · TTFT 13.024 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
151Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
103,53 tok/s TG
Prefill 283 · TTFT 140.845 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
152Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
103,21 tok/s TG
Prefill 2.393 · TTFT 803 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
153Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
103,17 tok/s TG
Prefill 1.484 · TTFT 1.725 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
154Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
103,11 tok/s TG
Prefill 282 · TTFT 141.242 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
155Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
102,89 tok/s TG
Prefill 3.111 · TTFT 692 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
156Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
102,63 tok/s TG
Prefill 266 · TTFT 144.911 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
157Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
102,53 tok/s TG
Prefill 311 · TTFT 161.346 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
158Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
102,46 tok/s TG
Prefill 10.458 · TTFT 1.708 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawBF16
159Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
102,20 tok/s TG
Prefill 309 · TTFT 162.437 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
160Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
102,00 tok/s TG
Prefill 264 · TTFT 145.506 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
161Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
101,58 tok/s TG
Prefill 308 · TTFT 162.990 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
162Codestral-22B-v0.122BMistral AI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
101,58 tok/s TG
Prefill 2.196 · TTFT 16.679 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
163Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
101,05 tok/s TG
Prefill 268 · TTFT 145.152 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
164Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
100,84 tok/s TG
Prefill 268 · TTFT 146.060 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
165Qwen3.5-122B-A10B122BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
100,64 tok/s TG
Prefill 10.369 · TTFT 1.153 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawGPTQ
166Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
100,45 tok/s TG
Prefill 265 · TTFT 146.219 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
167Qwen3-Omni-30B-A3B-Thinking30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
100,28 tok/s TG
Prefill 10.572 · TTFT 1.487 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ
168Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
100,21 tok/s TG
Prefill 266 · TTFT 147.297 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
169Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
99,92 tok/s TG
Prefill 2.124 · TTFT 903 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
170Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
99,85 tok/s TG
Prefill 266 · TTFT 147.215 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
171Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
99,82 tok/s TG
Prefill 1.006 · TTFT 5.090 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
172gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
99,77 tok/s TG
Prefill 1.920 · TTFT 1.022 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
173gpt-oss-120b120BOpenAI Performance benchmark
99,77 tok/s TG
Prefill 1.920 · TTFT 1.022 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
174Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
99,65 tok/s TG
Prefill 266 · TTFT 147.433 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
175Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
99,59 tok/s TG
Prefill 264 · TTFT 148.312 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
176Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
98,95 tok/s TG
Prefill 2.674 · TTFT 916 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
177Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
98,79 tok/s TG
Prefill 1.311 · TTFT 9.807 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
178Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
97,61 tok/s TG
Prefill 2.827 · TTFT 862 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
179Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmark
97,61 tok/s TG
Prefill 2.827 · TTFT 862 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
180Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
97,18 tok/s TG
Prefill 2.418 · TTFT 2.117 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
181Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
95,78 tok/s TG
Prefill 1.777 · TTFT 2.881 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
182gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
94,93 tok/s TG
Prefill 206 · TTFT 56.638 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
183Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
94,76 tok/s TG
Prefill 3.651 · TTFT 1.402 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
184gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
94,39 tok/s TG
Prefill 208 · TTFT 56.248 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
185Seed-OSS-36B-Instruct36BByteDance Seed Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
93,75 tok/s TG
Prefill 2.324 · TTFT 9.824 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
186Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
93,53 tok/s TG
Prefill 2.671 · TTFT 192 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
187Nemotron-3-Nano-4B4BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
93,42 tok/s TG
Prefill 2.630 · TTFT 822 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
188gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
92,91 tok/s TG
Prefill 206 · TTFT 56.755 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
189Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
91,48 tok/s TG
Prefill 3.221 · TTFT 159 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
190Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
91,39 tok/s TG
Prefill 4.034 · TTFT 603 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
191Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark
91,39 tok/s TG
Prefill 4.034 · TTFT 603 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
192Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
90,98 tok/s TG
Prefill 4.283 · TTFT 569 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
193Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmark
90,98 tok/s TG
Prefill 4.283 · TTFT 569 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
194Nemotron-3.5-Lightning-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
90,81 tok/s TG
Prefill 3.309 · TTFT 155 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
195Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
89,84 tok/s TG
Prefill 4.031 · TTFT 605 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclaw
196Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
89,35 tok/s TG
Prefill 1.608 · TTFT 8.030 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
197Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
88,90 tok/s TG
Prefill 7.618 · TTFT 2.214 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
198Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
88,86 tok/s TG
Prefill 1.184 · TTFT 4.324 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
199Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
88,58 tok/s TG
Prefill 4.831 · TTFT 503 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
200Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark
88,58 tok/s TG
Prefill 4.831 · TTFT 503 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
201Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
88,22 tok/s TG
Prefill 5.195 · TTFT 470 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
202Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
88,22 tok/s TG
Prefill 5.195 · TTFT 470 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
203Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
87,92 tok/s TG
Prefill 4.116 · TTFT 600 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
204Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
87,84 tok/s TG
Prefill 2.455 · TTFT 1.018 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
205Qwen3-30B-A3B-Thinking-250730BQwen (Alibaba) Performance benchmark
87,84 tok/s TG
Prefill 2.455 · TTFT 1.018 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
206North-Mini-Code-1.0Cohere Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
87,33 tok/s TG
Prefill 3.234 · TTFT 648 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
207Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
87,03 tok/s TG
Prefill 3.930 · TTFT 629 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
208Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
86,76 tok/s TG
Prefill 4.914 · TTFT 497 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclaw
209Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
86,73 tok/s TG
Prefill 2.139 · TTFT 2.394 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
210Qwen3-VL-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
86,67 tok/s TG
Prefill 2.692 · TTFT 903 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclaw
211Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
86,56 tok/s TG
Prefill 2.914 · TTFT 1.757 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
212Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
86,42 tok/s TG
Prefill 1.538 · TTFT 18.622 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
213Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
86,40 tok/s TG
Prefill 1.833 · TTFT 17.736 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
214Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
85,98 tok/s TG
Prefill 6.398 · TTFT 386 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
215Meta-Llama-3.1-8B-Instruct8BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
84,89 tok/s TG
Prefill 8.039 · TTFT 307 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
216Qwen3.6-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
84,27 tok/s TG
Prefill 1.006 · TTFT 21.945 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
217Muse-Glimmer-30B30BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
84,05 tok/s TG
Prefill 2.716 · TTFT 943 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
218Muse-Glimmer-30B30BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
82,79 tok/s TG
Prefill 2.200 · TTFT 1.164 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
219Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
82,49 tok/s TG
Prefill 3.953 · TTFT 587 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
220Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
82,49 tok/s TG
Prefill 3.953 · TTFT 587 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
221Qwen3.8-27B27BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
81,20 tok/s TG
Prefill 5.042 · TTFT 2.489 ms
5×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawAWQ-INT4
222Nemotron-3-Super-120B-A12B120BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
80,54 tok/s TG
Prefill 1.417 · TTFT 3.615 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ4_K_M
223Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
79,36 tok/s TG
Prefill 2.286 · TTFT 843 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
224Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmark
79,36 tok/s TG
Prefill 2.286 · TTFT 843 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
225Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
78,90 tok/s TG
Prefill 4.644 · TTFT 504 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
226Qwen3-30B-A3B-Instruct-250730BQwen (Alibaba) Performance benchmark
78,90 tok/s TG
Prefill 4.644 · TTFT 504 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
227Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
78,72 tok/s TG
Prefill 575 · TTFT 11.195 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
228Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
78,68 tok/s TG
Prefill 193 · TTFT 220.912 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
229Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
78,54 tok/s TG
Prefill 2.337 · TTFT 875 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
230Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmark
78,54 tok/s TG
Prefill 2.337 · TTFT 875 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
231Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
78,46 tok/s TG
Prefill 2.327 · TTFT 829 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
232Qwen3.5-35B-A3B35BQwen (Alibaba) Performance benchmark
78,46 tok/s TG
Prefill 2.327 · TTFT 829 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
233Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
78,25 tok/s TG
Prefill 2.525 · TTFT 867 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
234Ling-3.0-flash127.5BinclusionAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
78,19 tok/s TG
Prefill 1.532 · TTFT 9.080 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
235Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
77,28 tok/s TG
Prefill 2.856 · TTFT 676 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
236Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
77,25 tok/s TG
Prefill 192 · TTFT 223.583 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
237Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
76,95 tok/s TG
Prefill 193 · TTFT 224.160 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
238Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
76,74 tok/s TG
Prefill 3.638 · TTFT 530 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
239Nemotron-Cascade-2-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
76,18 tok/s TG
Prefill 221 · TTFT 62.327 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
240Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,87 tok/s TG
Prefill 218 · TTFT 62.625 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
241Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,86 tok/s TG
Prefill 219 · TTFT 62.421 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
242Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,66 tok/s TG
Prefill 1.817 · TTFT 2.001 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
243Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmark
75,66 tok/s TG
Prefill 1.817 · TTFT 2.001 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
244Qwen3.6-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,65 tok/s TG
Prefill 3.157 · TTFT 162 ms
1×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppopenclaw_cli batched-bench ROCmQ8_0
245Nemotron-3-Nano-30B-A3B30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,47 tok/s TG
Prefill 218 · TTFT 62.596 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
246Nemotron-3-Nano-Omni-30B-A3B-Reasoning30BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,41 tok/s TG
Prefill 219 · TTFT 62.640 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
247Ornith-1.0-9B9BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,38 tok/s TG
Prefill 3.900 · TTFT 494 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawQ4_K_M
248Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,30 tok/s TG
Prefill 2.873 · TTFT 669 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
249Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmark
75,30 tok/s TG
Prefill 2.873 · TTFT 669 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawQ4_K_M
250Muse-Glimmer-30B30BMeta Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
75,28 tok/s TG
Prefill 2.774 · TTFT 8.886 ms
10×4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawBF16