Models /
Phi 4 Mini Instruct
3results
3devices
4.45Bparams
145fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 3090 | Q4_K - Medium | 145 | 5,535 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| RTX 4050 Laptop GPU | Q4_K - Medium | 50.5 | 2,065 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| AMD Radeon RX 6600 XT | Q6_K | 28.2 | 806 | LocalScore ↗ | 4,352 | 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.