Models /
Qwen3 Coder 0.6B 0.9B 7 1bR5 Nobs F16
2results
2devices
0.97Bparams
79.0fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 4050 Laptop GPU | Q4_K - Medium | 79.0 | 4,600 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| GTX 1660 SUPER | F16 | 14.8 | 317 | 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.