🏆
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 | OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 116,53 tok/s TG Prefill 1.848 · TTFT 16.560 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 2 | OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 54,60 tok/s TG Prefill 1.544 · TTFT 9.340 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 3 | OpenReasoning-Nemotron-32B32BNVIDIA Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,60 tok/s TG Prefill 916 · TTFT 2.675 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |

