RTX 4050 Laptop GPU × SmolLM2 135M Instruct
SmolLM2 135M Instruct on RTX 4050 Laptop GPU
152best gen tok/s
13,269best prompt tok/s
640max context tested
5results
Measured · all numbers below come from the linked sources
llama.cpp
5 tiny/test model result(s) (excluded from headlines)
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_0 | 152 | 13,164 | LocalScore ↗ | 512+128 | 119 ms | llamafile 0.9.3 |
| Q4_K - Medium | 145 | 13,269 | LocalScore ↗ | 512+128 | 121 ms | llamafile 0.9.3 |
| Q4_K - Medium | 129 | 13,112 | LocalScore ↗ | 512+128 | 120 ms | llamafile 0.9.3 |
| IQ1_S - 1.5625 bpw | 35.4 | 739 | LocalScore ↗ | 512+128 | 1,589 ms | llamafile 0.9.3 |
| IQ4_XS - 4.25 bpw | 35.0 | 860 | LocalScore ↗ | 512+128 | 1,356 ms | llamafile 0.9.3 |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
"Context tested" is the largest prompt+generation length actually benchmarked (tokens), not a memory-fit estimate.
What else can RTX 4050 Laptop GPU run? →
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.