RTX 4050 Laptop GPU × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on RTX 4050 Laptop GPU
132best gen tok/s
5,332best prompt tok/s
4,352max context tested
4results
Measured · all numbers below come from the linked sources
llama.cpp
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_K - Medium | 132 | 5,332 | LocalScore ↗ | 512+128 | 285 ms | llamafile 0.9.3 |
| Q4_K - Medium | 132 | 5,231 | LocalScore ↗ | 4,352 | 282 ms | llamafile 0.9.3 |
| Q4_K - Medium | 114 | 4,979 | LocalScore ↗ | 512+128 | 286 ms | llamafile 0.9.2 |
| Q4_K - Medium | 94.1 | 4,127 | LocalScore ↗ | 4,352 | 350 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.