RTX 4050 Laptop GPU × Raincandy U TinyStories 656K
Raincandy U TinyStories 656K on RTX 4050 Laptop GPU
1,885best gen tok/s
153,940best prompt tok/s
640max context tested
3results
Measured · all numbers below come from the linked sources
llama.cpp
3 tiny/test model result(s) (excluded from headlines)
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_K - Medium | 1,885 | 153,940 | LocalScore ↗ | 512+128 | 9 ms | llamafile 0.9.3 |
| Q8_0 | 1,823 | 153,794 | LocalScore ↗ | 512+128 | 9 ms | llamafile 0.9.3 |
| Q2_K - Medium | 640 | 27,724 | LocalScore ↗ | 512+128 | 57 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.