Hardware /
Apple M2 Pro (16-core GPU)
20measured results
91.5best gen tok/s*
32 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 | 91.5 | 1,341 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 91.5 | 1,281 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 91.0 | 1,347 | LocalScore ↗ | 4,352 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 90.9 | 1,305 | LocalScore ↗ | 4,352 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 90.8 | 1,316 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 37.9 | 294 | llama.cpp (Metal) ↗ | 512+128 | llama.cpp Metal | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 25.0 | 229 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 24.5 | 224 | LocalScore ↗ | 4,352 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 24.3 | 226 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 23.8 | 209 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 23.6 | 219 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| DeepSeek R1 0528 Qwen3 8B | Q4_K - Medium | 23.1 | 223 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Qwen3 8B | Q4_K - Medium | 23.0 | 223 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 2 7B | Q8_0 | 22.7 | 288 | llama.cpp (Metal) ↗ | 512+128 | llama.cpp Metal | Details → |
| Qwen3 14B | Q4_K - Medium | 13.9 | 123 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 13.4 | 119 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 13.3 | 117 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 13.3 | 119 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 13.3 | 118 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | F16 | 12.5 | 313 | llama.cpp (Metal) ↗ | 512+128 | llama.cpp Metal | 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.