Apple M1 Max (24-core GPU) × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on Apple M1 Max (24-core GPU)
106best gen tok/s
1,684best prompt tok/s
640max context tested
5results
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 | 106 | 1,684 | LocalScore ↗ | 512+128 | 682 ms | llamafile 0.9.2 |
| Q4_K - Medium | 106 | 1,644 | LocalScore ↗ | 512+128 | 697 ms | llamafile 0.9.2 |
| Q4_K - Medium | 105 | 1,680 | LocalScore ↗ | 512+128 | 688 ms | llamafile 0.9.2 |
| Q4_K - Medium | 105 | 1,627 | LocalScore ↗ | 512+128 | 708 ms | llamafile 0.9.2 |
| Q4_K - Medium | 83.0 | 1,537 | LocalScore ↗ | 512+128 | 740 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 M1 Max (24-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.