Models /

Ministral 8B Instruct 2410 TEST

2results
2devices
8.02Bparams
86.6fastest gen tok/s

llama.cpp

HardwareQuantGen tok/sPrompt tok/sSourceContext testedBuild
RTX A5000Q4_K - Medium86.62,817LocalScore ↗512+128llamafile 0.9.2Details →
RTX 4070 TiQ6_K54.23,200LocalScore ↗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.