Models /

TinyStories 656K

23results
1devices
0.00Bparams

llama.cpp

23 tiny/test model result(s) (excluded from headlines)
HardwareQuantGen tok/sPrompt tok/sSourceContext testedBuild
RTX 4050 Laptop GPUQ4_K - Medium1,905145,343LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_K - Medium1,890144,854LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ5_11,890145,629LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ5_K - Small1,890142,236LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_11,887148,849LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_K - Small1,885140,884LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ5_K - Medium1,879153,054LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ6_K1,873159,348LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ5_K - Medium1,869145,396LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_01,859147,634LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ5_01,856154,382LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ4_K - Medium1,732153,201LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ3_K - Medium89838,782LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ3_K - Large86539,062LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ3_K - Medium85432,354LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUIQ3_S mix - 3.66 bpw72821,230LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUIQ4_XS - 4.25 bpw67415,970LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUIQ4_NL - 4.5 bpw65125,663LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ2_K - Medium64621,761LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUIQ4_XS - 4.25 bpw62530,058LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUIQ3_S - 3.4375 bpw61723,654LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUIQ3_XS - 3.3 bpw61724,298LocalScore ↗512+128llamafile 0.9.3Details →
RTX 4050 Laptop GPUQ3_K - Small55714,647LocalScore ↗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.