🏆
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-2.1-INT433.4BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,88 tok/s TG Prefill 3.698 · TTFT 748 ms | 1× | 3x AMD Radeon AI PRO R9700 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawINT4 | Details → | |
| 2 | Laguna-XS-2.1-INT433.4BPoolside Performance benchmark | 26,88 tok/s TG Prefill 3.698 · TTFT 748 ms | 1× | 3x AMD Radeon AI PRO R9700 i32x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawINT4 | Details → |

