← CanIRunLocal · All hardware · All models
Yes. Qwen 2.5 Coder 14B fits in fast memory on M3 24GB at Q5_K_M (12.3 GB needed, 16.1 GB usable), about 7 tok/s (estimate).
Hardware: M3 24GB · Model: Qwen 2.5 Coder 14B
M3 24GB has 24 GB of unified memory and 100 GB/s of memory bandwidth. M2 24GB has the same memory and bandwidth, so the fit numbers match; this page is M3 24GB. The checker leaves macOS a share of unified memory, so Ollama can use 16.1 GB. Qwen 2.5 Coder 14B (14.8B, Alibaba) at Q5_K_M is a 11 GB download and needs 12.3 GB with headroom for about 8k tokens.
| Best quant | Q5_K_M |
|---|---|
| Download size | 11 GB |
| Memory needed | 12.3 GB |
| Usable fast memory | 16.1 GB |
| Fit | fits in fast memory |
| Estimated speed | ~7 tok/s (estimate) |
| Command | ollama run qwen2.5-coder:14b-instruct-q5_K_M |
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