Models /
gemma-2-9b-it
3results
3devices
10.16Bparams
36.4fastest gen tok/s
llama.cpp
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 3060 | Q4_K - Medium | 36.4 | 1,217 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Apple M4 Max (32-core GPU) | Q4_K - Medium | 36.3 | 418 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| RTX 4060 Ti | Q4_K - Medium | 32.4 | 1,820 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | 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.