# Can I run Phi-4-mini 3.8B on Apple M4 (24GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~3.8 GB of ~16 GB usable. You have room for FP16 for higher quality.

- Model: 3.8B, Q4_K_M 2.49 GB
- Device: 24 GB unified, ~16 GB usable for weights
- Needs ~3.8 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on macOS: LM Studio
- Command: `ollama run phi4-mini:3.8b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/phi4-mini, https://ollama.com/library/phi4-mini/tags, https://huggingface.co/bartowski/microsoft_Phi-4-mini-instruct-GGUF.

More: https://localmodel.run/can-i-run/phi-4-mini-3.8b/apple-m4-24gb