Models /

Granite 3.1 8b Instruct

1results
1devices
8.37Bparams
30.6fastest gen tok/s

llama.cpp

HardwareQuantGen tok/sPrompt tok/sSourceContext testedBuild
AMD Radeon RX 7800 XTQ4_K - Medium30.6487LocalScore ↗512+128llamafile 0.9.3Details →

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.