← CanIRunLocal · All hardware · All models
Yes. Qwen 2.5 Coder 14B fits in fast memory on M3 Pro 18GB at Q4_K_M (10.3 GB needed, 12.1 GB usable), about 13 tok/s (estimate).
Hardware: M3 Pro 18GB · Model: Qwen 2.5 Coder 14B
M3 Pro 18GB has 18 GB of unified memory and 150 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 12.1 GB. Qwen 2.5 Coder 14B (14.8B, Alibaba) at Q4_K_M is a 9 GB download and needs 10.3 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 9 GB |
| Memory needed | 10.3 GB |
| Usable fast memory | 12.1 GB |
| Fit | fits in fast memory |
| Estimated speed | ~13 tok/s (estimate) |
| Command | ollama run qwen2.5-coder:14b |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt