Hardware /
RTX 4060 Laptop GPU
8measured results
192best gen tok/s*
8 GBreported memory
*Headline excludes tiny/test models (under 0.6B params or TinyStories-style). Open in rig checker →
llama.cpp
| Model | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | Q4_K - Medium | 192 | 6,950 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 97.3 | 6,259 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 95.6 | 6,191 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 60.0 | 2,358 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @a5c07dc — coopmat2 | Details → |
| Llama 2 7B | Q4_0 | 59.5 | 2,136 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @a5c07dc — coopmat2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 43.4 | 1,695 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 40.3 | 1,591 | LocalScore ↗ | 4,352 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 24.3 | 809 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
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.