RTX 4060 Laptop GPU × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on RTX 4060 Laptop GPU
43.4best gen tok/s
1,695best prompt tok/s
4,352max context tested
3results
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 | 43.4 | 1,695 | LocalScore ↗ | 512+128 | 800 ms | llamafile 0.9.2 |
| Q4_K - Medium | 40.3 | 1,591 | LocalScore ↗ | 4,352 | 847 ms | llamafile 0.9.3 |
| Q4_K - Medium | 24.3 | 809 | LocalScore ↗ | 512+128 | 9,092 ms | llamafile 0.9.2 |
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 4060 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.