🏆
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
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.764,99 tok/s TG Prefill 8.542 · TTFT 7.776 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 2 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.757,37 tok/s TG Prefill 9.025 · TTFT 7.343 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.753,82 tok/s TG Prefill 9.267 · TTFT 7.329 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.740,43 tok/s TG Prefill 9.653 · TTFT 7.258 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.740,12 tok/s TG Prefill 8.571 · TTFT 7.786 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 6 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.738,38 tok/s TG Prefill 8.872 · TTFT 7.722 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 7 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.629,91 tok/s TG Prefill 11.384 · TTFT 7.322 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.620,45 tok/s TG Prefill 10.729 · TTFT 7.428 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.620,41 tok/s TG Prefill 12.519 · TTFT 7.197 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 10 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.615,26 tok/s TG Prefill 13.041 · TTFT 7.166 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 11 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.611,02 tok/s TG Prefill 12.725 · TTFT 7.223 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.609,12 tok/s TG Prefill 10.883 · TTFT 7.452 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 13 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.608,39 tok/s TG Prefill 11.312 · TTFT 7.410 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 14 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.607,66 tok/s TG Prefill 10.675 · TTFT 7.505 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 15 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.606,11 tok/s TG Prefill 12.690 · TTFT 7.203 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 16 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.554,46 tok/s TG Prefill 7.954 · TTFT 8.418 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 17 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.533,70 tok/s TG Prefill 6.831 · TTFT 8.783 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 18 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.532,89 tok/s TG Prefill 7.482 · TTFT 8.633 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 986,05 tok/s TG Prefill 5.179 · TTFT 13.058 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 20 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 981,72 tok/s TG Prefill 5.166 · TTFT 13.134 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 21 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 979,74 tok/s TG Prefill 5.175 · TTFT 13.143 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 22 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 975,10 tok/s TG Prefill 7.343 · TTFT 2.879 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 23 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 972,04 tok/s TG Prefill 7.593 · TTFT 2.866 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 24 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 967,89 tok/s TG Prefill 8.250 · TTFT 2.709 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 25 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 966,13 tok/s TG Prefill 8.310 · TTFT 2.703 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 965,66 tok/s TG Prefill 7.691 · TTFT 2.852 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 27 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 959,86 tok/s TG Prefill 7.429 · TTFT 2.902 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 28 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 877,73 tok/s TG Prefill 9.525 · TTFT 2.629 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 876,74 tok/s TG Prefill 9.643 · TTFT 2.610 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 875,59 tok/s TG Prefill 11.578 · TTFT 2.412 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 874,29 tok/s TG Prefill 9.000 · TTFT 2.704 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 871,83 tok/s TG Prefill 11.767 · TTFT 2.401 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 871,77 tok/s TG Prefill 11.025 · TTFT 2.465 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 871,59 tok/s TG Prefill 9.810 · TTFT 2.601 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 869,75 tok/s TG Prefill 11.997 · TTFT 2.389 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 869,07 tok/s TG Prefill 7.024 · TTFT 3.115 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 865,51 tok/s TG Prefill 12.041 · TTFT 2.375 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 861,53 tok/s TG Prefill 6.372 · TTFT 3.336 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 861,47 tok/s TG Prefill 6.618 · TTFT 3.232 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 40 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 836,37 tok/s TG Prefill 39.157 · TTFT 1.033 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 41 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 810,27 tok/s TG Prefill 7.685 · TTFT 13.735 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 806,94 tok/s TG Prefill 7.252 · TTFT 13.902 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 44 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 712,04 tok/s TG Prefill 35.143 · TTFT 1.137 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 45 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 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 RAM | vLLMgodclawFP8 | Details → | |
| 46 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 586,52 tok/s TG Prefill 4.479 · TTFT 4.845 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 47 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 584,39 tok/s TG Prefill 4.467 · TTFT 4.864 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 48 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 582,20 tok/s TG Prefill 4.480 · TTFT 4.869 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 49 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 580,46 tok/s TG Prefill 29.873 · TTFT 587 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 50 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 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 RAM | vLLMgodclawAWQ | Details → | |
| 51 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 502,52 tok/s TG Prefill 7.839 · TTFT 8.284 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 52 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 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 RAM | vLLMopenclaw_cliAWQ | Details → | |
| 53 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 477,43 tok/s TG Prefill 7.813 · TTFT 8.277 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 54 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 467,41 tok/s TG Prefill 6.778 · TTFT 4.374 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 55 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 463,93 tok/s TG Prefill 6.756 · TTFT 4.404 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 56 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 462,23 tok/s TG Prefill 24.899 · TTFT 645 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 57 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 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 RAM | vLLMgodclawFP8 | Details → | |
| 58 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 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 RAM | vLLMopenclaw_cliFP8 | Details → | |
| 59 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 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 RAM | vLLMopenclaw_cliAWQ | Details → | |
| 60 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 319,02 tok/s TG Prefill 1.498 · TTFT 42.331 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 61 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 318,94 tok/s TG Prefill 1.446 · TTFT 42.781 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 62 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 318,47 tok/s TG Prefill 1.427 · TTFT 42.816 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 63 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 318,17 tok/s TG Prefill 1.479 · TTFT 42.546 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 64 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 316,35 tok/s TG Prefill 1.470 · TTFT 42.801 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 65 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 316,28 tok/s TG Prefill 1.496 · TTFT 42.551 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 66 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 310,19 tok/s TG Prefill 5.706 · TTFT 484 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 67 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 309,93 tok/s TG Prefill 4.887 · TTFT 562 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 68 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 309,54 tok/s TG Prefill 5.382 · TTFT 511 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 69 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 308,34 tok/s TG Prefill 5.678 · TTFT 484 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 70 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 308,21 tok/s TG Prefill 5.712 · TTFT 481 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 71 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 307,85 tok/s TG Prefill 5.879 · TTFT 467 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 72 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 276,05 tok/s TG Prefill 4.855 · TTFT 565 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 73 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 275,74 tok/s TG Prefill 5.897 · TTFT 466 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 74 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 275,54 tok/s TG Prefill 4.697 · TTFT 600 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 75 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 274,31 tok/s TG Prefill 6.386 · TTFT 430 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 76 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 273,91 tok/s TG Prefill 8.295 · TTFT 331 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 77 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 273,83 tok/s TG Prefill 4.894 · TTFT 561 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 78 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 273,64 tok/s TG Prefill 6.739 · TTFT 408 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 79 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 273,58 tok/s TG Prefill 6.464 · TTFT 425 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 80 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 273,45 tok/s TG Prefill 7.505 · TTFT 373 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 81 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 261,01 tok/s TG Prefill 15.938 · TTFT 1.003 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 82 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 237,96 tok/s TG Prefill 6.516 · TTFT 2.127 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 83 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 237,53 tok/s TG Prefill 6.972 · TTFT 1.971 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 84 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 205,50 tok/s TG Prefill 1.351 · TTFT 15.992 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 85 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 205,02 tok/s TG Prefill 1.348 · TTFT 16.034 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 86 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 205,02 tok/s TG Prefill 1.327 · TTFT 16.066 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 87 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,44 tok/s TG Prefill 1.300 · TTFT 16.378 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 88 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 204,31 tok/s TG Prefill 1.375 · TTFT 15.932 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 89 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 203,41 tok/s TG Prefill 1.372 · TTFT 16.012 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 90 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,34 tok/s TG Prefill 3.833 · TTFT 717 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 91 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,29 tok/s TG Prefill 3.814 · TTFT 720 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 92 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 198,25 tok/s TG Prefill 3.820 · TTFT 720 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 93 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 188,89 tok/s TG Prefill 12.970 · TTFT 212 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 94 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 174,29 tok/s TG Prefill 10.685 · TTFT 258 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 95 | Laguna-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 RAM | vLLMgodclawINT4 | Details → | |
| 96 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 152,89 tok/s TG Prefill 4.988 · TTFT 551 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 97 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 152,50 tok/s TG Prefill 4.956 · TTFT 555 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 98 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 147,92 tok/s TG Prefill 11.709 · TTFT 234 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 99 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 143,51 tok/s TG Prefill 8.883 · TTFT 309 ms | 1× | NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliAWQ | Details → | |
| 100 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 137,12 tok/s TG Prefill 10.007 · TTFT 275 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 101 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 126,89 tok/s TG Prefill 5.003 · TTFT 550 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 102 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 126,49 tok/s TG Prefill 5.012 · TTFT 548 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 103 | Laguna-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 RAM | llama.cppgodclawQ4_K_M | Details → | |
| 104 | Laguna-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 RAM | llama.cppgodclawQ4_K_M | Details → | |
| 105 | Laguna-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 RAM | llama.cppgodclawQ4_K_M | Details → | |
| 106 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 94,59 tok/s TG Prefill 7.915 · TTFT 347 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMopenclaw_cliFP8 | Details → | |
| 107 | Laguna-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 RAM | vLLMgodclawINT4 | Details → | |
| 108 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,50 tok/s TG Prefill 1.209 · TTFT 2.272 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 109 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,39 tok/s TG Prefill 1.195 · TTFT 2.302 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 110 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,20 tok/s TG Prefill 1.206 · TTFT 2.277 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 111 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,85 tok/s TG Prefill 254 · TTFT 70.881 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 112 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,82 tok/s TG Prefill 253 · TTFT 70.884 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 113 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 67,59 tok/s TG Prefill 252 · TTFT 71.355 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 114 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 30,25 tok/s TG Prefill 204 · TTFT 13.469 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 115 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,97 tok/s TG Prefill 203 · TTFT 13.549 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 116 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,67 tok/s TG Prefill 203 · TTFT 13.592 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 117 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,88 tok/s TG Prefill 3.698 · TTFT 748 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawINT4 | Details → | |
| 118 | Laguna-XS-2.1Poolside Performance benchmark | 26,88 tok/s TG Prefill 3.698 · TTFT 748 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawINT4 | Details → |
