🏆
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 | Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 325,24 tok/s TG Prefill 9.520 · TTFT 2.933 ms | 10× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 2 | Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 212,67 tok/s TG Prefill 6.514 · TTFT 1.882 ms | 5× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → | |
| 3 | Qwen3-4B4BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 85,07 tok/s TG Prefill 5.545 · TTFT 440 ms | 1× | AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAM | llama.cppopenclaw_cliQ8_0 | Details → |