Models /
SmolLM2 135M Instruct
5results
1devices
0.16Bparams
llama.cpp
5 tiny/test model result(s) (excluded from headlines)
| Hardware | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| RTX 4050 Laptop GPU | Q4_0 | 152 | 13,164 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| RTX 4050 Laptop GPU | Q4_K - Medium | 145 | 13,269 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| RTX 4050 Laptop GPU | Q4_K - Medium | 129 | 13,112 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| RTX 4050 Laptop GPU | IQ1_S - 1.5625 bpw | 35.4 | 739 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| RTX 4050 Laptop GPU | IQ4_XS - 4.25 bpw | 35.0 | 860 | 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.