Phi · 3.8B · In LM Mini

Phi-4 Mini Instruct on a phone

Strong reasoning in a phone-friendly package — great for explanations and code-ish help.

Parameters
3.8B
Typical Q4
~2.3–2.4 GB
RAM to budget
~3.6 GB
Engines
GGUF · MLX

Get it running

microsoft/Phi-4-mini-instruct (~3.8B). GGUF + MLX. Hugging Face: microsoft/Phi-4-mini-instruct.

In the LM Mini on-device catalog.

Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.

Phones that can run it

Tight (close other apps)