🏆
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 | Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 315,16 tok/s TG Prefill 13.007 · TTFT 3.960 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 2 | Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 260,23 tok/s TG Prefill 6.946 · TTFT 3.919 ms | 10× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 224,00 tok/s TG Prefill 10.578 · TTFT 1.518 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → | |
| 4 | Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 165,72 tok/s TG Prefill 4.638 · TTFT 2.673 ms | 5× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,22 tok/s TG Prefill 3.537 · TTFT 698 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,07 tok/s TG Prefill 577 · TTFT 23.820 ms | 5× | AMD Oberon (PlayStation 5)AMD Zen2 8-Core (PlayStation 5) · 16 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 7 | Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,58 tok/s TG Prefill 373 · TTFT 6.570 ms | 1× | AMD Oberon (PlayStation 5)AMD Zen2 8-Core (PlayStation 5) · 16 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | Qwen3-8B8.2BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,36 tok/s TG Prefill 4.818 · TTFT 505 ms | 1× | 2x AMD Radeon RX 7900 XTXAMD Ryzen Threadripper PRO 3955WX 16-Cores · 63 GB RAM | vLLMgodclaw | Details → |