Models /

Minueza 2 96M Instruct Variant 03

19results
1devices
0.10Bparams

llama.cpp

19 tiny/test model result(s) (excluded from headlines)
HardwareQuantGen tok/sPrompt tok/sSourceContext testedBuild
RTX 4050 Laptop GPUQ4_052234,113LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ5_052132,770LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ5_151730,545LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_K - Small51732,351LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_K - Medium51332,676LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_151033,013LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ8_050933,036LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ6_K50232,163LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ5_K - Medium50231,486LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_K - Medium50233,450LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_K - Medium47832,105LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_045933,267LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUBF1623923,089LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ3_K - Medium1751,976LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ3_K - Large1722,096LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUIQ4_NL - 4.5 bpw1281,546LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUIQ4_XS - 4.25 bpw1251,483LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ3_K - Small1251,431LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ2_K - Medium1231,464LocalScore ↗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.