Models /

Gemma 3 12b

2results
1devices
12.77Bparams
40.1fastest gen tok/s

llama.cpp

HardwareQuantGen tok/sPrompt tok/sSourceContext testedBuild
Quadro RTX 6000Q4_040.11,384LocalScore ↗512+128llamafile 0.9.2Details →
Quadro RTX 6000Q4_039.71,376LocalScore ↗512+128llamafile 0.9.2Details →

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.