🏆
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 | Qwen2.5-1.5B-InstructQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,14 tok/s TG Prefill 67 · TTFT 194.902 ms | 5× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 2 | Qwen2.5-1.5B-InstructQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,93 tok/s TG Prefill 47 · TTFT 52.732 ms | 1× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 3 | Qwen2.5-1.5B-InstructQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,11 tok/s TG Prefill 91 · TTFT 301.409 ms | 10× | Keine GPU (CPU-only) i4 x Cortex-A78C + 4 x Cortex-A55 · 15 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |