Models /
llama
4results
1devices
0.00Bparams
llama.cpp
4 tiny/test model result(s) (excluded from headlines)
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 4050 Laptop GPU | all F32 (guessed) | 908 | 92,104 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| RTX 4050 Laptop GPU | Q6_K | 846 | 79,711 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| RTX 4050 Laptop GPU | Q4_K - Medium | 844 | 87,067 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| RTX 4050 Laptop GPU | IQ4_XS - 4.25 bpw | 279 | 13,888 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
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.