Models /
Granite 3.3 8b Instruct
3results
3devices
8.37Bparams
40.4fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 4070 Ti | Q8_0 | 40.4 | 3,211 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| RTX 3050 | Q4_K - Medium | 23.5 | 594 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Apple M4 Pro (20-core GPU) | Q5_K - Medium | 23.0 | 276 | 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.