llama on RTX 4050 Laptop GPU
908best gen tok/s
92,104best prompt tok/s
640max context tested
4results
Measured · all numbers below come from the linked sources
llama.cpp
4 tiny/test model result(s) (excluded from headlines)
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| all F32 (guessed) | 908 | 92,104 | LocalScore ↗ | 512+128 | 17 ms | llamafile 0.9.3 |
| Q6_K | 846 | 79,711 | LocalScore ↗ | 512+128 | 21 ms | llamafile 0.9.3 |
| Q4_K - Medium | 844 | 87,067 | LocalScore ↗ | 512+128 | 19 ms | llamafile 0.9.3 |
| IQ4_XS - 4.25 bpw | 279 | 13,888 | LocalScore ↗ | 512+128 | 116 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.