Models /
Qwen3 14B
4results
4devices
14.77Bparams
39.3fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 3090 | Q3_K - Large | 39.3 | 1,604 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| AMD Radeon RX 7800 XT | Q4_K - Medium | 24.1 | 324 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Apple M2 Pro (16-core GPU) | Q4_K - Medium | 13.9 | 123 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| RTX 4060 Ti | Q4_K - Medium | 11.9 | 1,091 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
Includes results from LocalScore, a Mozilla Builders project by cjpais, mirrored in the cn0303/local-llm-speed-benchmarks dataset. LocalScore runs use llamafile, which is built on llama.cpp.