Hardware /
RTX 3060 Laptop GPU
28measured results
210best gen tok/s*
6 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 | 210 | 6,386 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 181 | 5,836 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 162 | 6,037 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 160 | 6,037 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 160 | 5,174 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 157 | 5,787 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 153 | 6,016 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 148 | 5,276 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 136 | 4,902 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 135 | 4,908 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 126 | 5,096 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| active | Q2_K - Medium | 111 | 3,938 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| active | Q2_K - Medium | 101 | 3,970 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 86.4 | 3,700 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Gemma 3 1b It | Q4_K - Medium | 73.8 | 6,477 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 49.0 | 1,060 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @dbb3a47 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 45.5 | 1,439 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 45.2 | 1,450 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 45.1 | 1,410 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 44.5 | 1,426 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 43.5 | 1,265 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 39.8 | 1,250 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 38.4 | 1,094 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 34.8 | 1,050 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 30.0 | 891 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Gemma 3 1b It | BF16 | 22.1 | 3,121 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Gemma 3 1b It | BF16 | 21.0 | 2,679 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 1.1 | 82.9 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | 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.