Apple M2 Pro (19-core GPU) × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on Apple M2 Pro (19-core GPU)
104best gen tok/s
1,508best prompt tok/s
640max context tested
6results
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 | 104 | 1,508 | LocalScore ↗ | 512+128 | 793 ms | llamafile 0.9.2 |
| Q4_K - Medium | 100 | 1,473 | LocalScore ↗ | 512+128 | 806 ms | llamafile 0.9.2 |
| Q4_K - Medium | 99.6 | 1,485 | LocalScore ↗ | 512+128 | 811 ms | llamafile 0.9.2 |
| Q4_K - Medium | 99.5 | 1,458 | LocalScore ↗ | 512+128 | 809 ms | llamafile 0.9.2 |
| Q4_K - Medium | 99.3 | 1,495 | LocalScore ↗ | 512+128 | 803 ms | llamafile 0.9.2 |
| Q4_K - Medium | 98.0 | 1,477 | LocalScore ↗ | 512+128 | 819 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 Apple M2 Pro (19-core 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.