← CanIRunLocal · All hardware · All models
Yes. Phi-4 14B fits in fast memory on M3 16GB at Q4_K_M (10.4 GB needed, 10.7 GB usable), about 9 tok/s (estimate).
Hardware: M3 16GB · Model: Phi-4 14B
M3 16GB has 16 GB of unified memory and 100 GB/s of memory bandwidth. M2 16GB has the same memory and bandwidth, so the fit numbers match; this page is M3 16GB. The checker leaves macOS a share of unified memory, so Ollama can use 10.7 GB. Phi-4 14B (14.7B, Microsoft) at Q4_K_M is a 9.1 GB download and needs 10.4 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 9.1 GB |
| Memory needed | 10.4 GB |
| Usable fast memory | 10.7 GB |
| Fit | fits in fast memory |
| Estimated speed | ~9 tok/s (estimate) |
| Command | ollama run phi4:14b |
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