Apple M2 Pro (16-core GPU) × Qwen2.5 14B Instruct
Qwen2.5 14B Instruct on Apple M2 Pro (16-core GPU)
13.4best gen tok/s
119best prompt tok/s
640max context tested
4results
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 | 13.4 | 119 | LocalScore ↗ | 512+128 | 10,579 ms | llamafile 0.9.3 |
| Q4_K - Medium | 13.3 | 117 | LocalScore ↗ | 512+128 | 10,703 ms | llamafile 0.9.2 |
| Q4_K - Medium | 13.3 | 119 | LocalScore ↗ | 512+128 | 10,665 ms | llamafile 0.9.2 |
| Q4_K - Medium | 13.3 | 118 | LocalScore ↗ | 512+128 | 10,680 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 (16-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.