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

LLM Leaderboard

Reale Messergebnisse aller getesteten Sprachmodelle auf echter, benannter Hardware – bewertet nach roher Geschwindigkeit (Performance in Token pro Sekunde, Prefill und Zeit bis zum ersten Token) und nach praktischer Aufgaben-Qualität in vollständigen Agenten- und Chat-Abläufen (Harness). Wähle unten einen Benchmark-Typ oder filtere nach Modell, Hersteller und Hardware, um genau zu sehen, was jeweils geprüft wird und wie die Ergebnisse zustande kommen.

⚡ Performance (tok/s)🤖 Harness-Qualität👥 Concurrency🖥️ echte Hardware
Reset
Messwert:
#Modell / HerstellerMesswerteParallelGPU / CPU / RAMRuntime
1Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
835,13 tok/s TG
Prefill 3.499 · TTFT 16.577 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
2Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
797,14 tok/s TG
Prefill 3.616 · TTFT 16.087 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
3Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
791,09 tok/s TG
Prefill 3.559 · TTFT 16.497 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
4Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
781,43 tok/s TG
Prefill 3.666 · TTFT 16.232 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawINT4
5Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
779,78 tok/s TG
Prefill 3.841 · TTFT 16.300 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
6Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
777,69 tok/s TG
Prefill 3.903 · TTFT 16.458 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
7Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
776,08 tok/s TG
Prefill 4.515 · TTFT 15.579 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
8Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
774,90 tok/s TG
Prefill 3.820 · TTFT 15.880 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
9Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
774,10 tok/s TG
Prefill 3.866 · TTFT 16.399 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
10Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
762,72 tok/s TG
Prefill 4.616 · TTFT 15.283 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
11Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
706,85 tok/s TG
Prefill 2.752 · TTFT 19.766 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
12Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
697,82 tok/s TG
Prefill 2.814 · TTFT 19.437 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
13Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
662,97 tok/s TG
Prefill 2.731 · TTFT 19.776 ms
10×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
14Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
470,52 tok/s TG
Prefill 3.067 · TTFT 6.420 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
15Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
465,82 tok/s TG
Prefill 3.019 · TTFT 6.496 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
16Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
461,99 tok/s TG
Prefill 3.219 · TTFT 6.266 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
17Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
456,52 tok/s TG
Prefill 3.165 · TTFT 6.386 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawINT4
18Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
440,78 tok/s TG
Prefill 3.886 · TTFT 5.752 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
19Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
437,16 tok/s TG
Prefill 3.329 · TTFT 6.298 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
20Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
434,94 tok/s TG
Prefill 3.365 · TTFT 6.267 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
21Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
434,78 tok/s TG
Prefill 3.944 · TTFT 5.525 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
22Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
429,63 tok/s TG
Prefill 3.334 · TTFT 6.284 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
23Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
415,35 tok/s TG
Prefill 3.365 · TTFT 5.876 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
24Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
413,18 tok/s TG
Prefill 2.358 · TTFT 8.016 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
25Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
408,67 tok/s TG
Prefill 2.354 · TTFT 8.049 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
26Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
405,17 tok/s TG
Prefill 2.414 · TTFT 7.850 ms
5×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
27Laguna-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 A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
28Laguna-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
29Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
250,44 tok/s TG
Prefill 13.079 · TTFT 1.402 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
30Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
234,43 tok/s TG
Prefill 11.921 · TTFT 1.518 ms
5×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
31Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
146,11 tok/s TG
Prefill 2.580 · TTFT 1.064 ms
1×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawUD-Q4_K_M
32Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
145,95 tok/s TG
Prefill 2.846 · TTFT 964 ms
1×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawINT4
33Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
135,75 tok/s TG
Prefill 3.130 · TTFT 877 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
34Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
135,51 tok/s TG
Prefill 2.905 · TTFT 945 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
35Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
135,22 tok/s TG
Prefill 2.941 · TTFT 933 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
36Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
135,13 tok/s TG
Prefill 2.928 · TTFT 938 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
37Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
133,97 tok/s TG
Prefill 2.205 · TTFT 1.246 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawINT4
38Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
131,71 tok/s TG
Prefill 2.197 · TTFT 1.250 ms
1×3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAMllama.cppgodclawUD-Q4_K_M
39Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
109,52 tok/s TG
Prefill 5.943 · TTFT 462 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
40Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
100,14 tok/s TG
Prefill 4.429 · TTFT 645 ms
1×2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
41Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
70,51 tok/s TG
Prefill 5.970 · TTFT 7.475 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
42Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
42,33 tok/s TG
Prefill 153 · TTFT 257.193 ms
10×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_M
43Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
42,20 tok/s TG
Prefill 4.890 · TTFT 4.010 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
44Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
32,82 tok/s TG
Prefill 177 · TTFT 255.495 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketINT4
45Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
32,70 tok/s TG
Prefill 134 · TTFT 130.995 ms
5×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_M
46Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
32,47 tok/s TG
Prefill 97 · TTFT 309.056 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
47Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
32,27 tok/s TG
Prefill 100 · TTFT 306.428 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
48Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
31,55 tok/s TG
Prefill 174 · TTFT 246.888 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketUD-Q4_K_M
49Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
31,51 tok/s TG
Prefill 98 · TTFT 302.732 ms
10×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
50Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
29,83 tok/s TG
Prefill 87 · TTFT 185.676 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
51Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
29,65 tok/s TG
Prefill 86 · TTFT 187.895 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
52Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
28,64 tok/s TG
Prefill 89 · TTFT 183.222 ms
5×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
53Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
25,54 tok/s TG
Prefill 157 · TTFT 125.314 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketUD-Q4_K_M
54Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
25,50 tok/s TG
Prefill 157 · TTFT 125.739 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketINT4
55Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
13,37 tok/s TG
Prefill 8.629 · TTFT 305 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMvLLMgodclawINT4
56Laguna-S-2.1-INT4Poolside Performancebenchmark
13,37 tok/s TG
Prefill 8.629 · TTFT 305 ms
1×3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMgodclawINT4
57Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
13,32 tok/s TG
Prefill 98 · TTFT 206.915 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_M
58Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
12,62 tok/s TG
Prefill 130 · TTFT 21.118 ms
1×NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAMllama.cppgodclawUD-Q4_K_M
59Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
11,64 tok/s TG
Prefill 76 · TTFT 36.235 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
60Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
11,60 tok/s TG
Prefill 76 · TTFT 36.406 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
61Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
11,44 tok/s TG
Prefill 76 · TTFT 36.141 ms
1×3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAMllama.cppgodclawUD-Q4_K_M
62Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
9,87 tok/s TG
Prefill 88 · TTFT 196.186 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_M
63Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
9,12 tok/s TG
Prefill 157 · TTFT 17.486 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketINT4
64Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
9,06 tok/s TG
Prefill 156 · TTFT 17.644 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAMllama.cppwebsocketUD-Q4_K_M
65Laguna-S-2.1-INT4Poolside PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation)
4,80 tok/s TG
Prefill 100 · TTFT 27.502 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliUD-Q4_K_M