Llama · 3B · In LM Mini

Llama 3.2 3B Instruct on a phone

Noticeably smarter than 1B — good for writing help and longer chats on Pro phones.

Parameters
3B
Typical Q4
~1.9–2.0 GB
RAM to budget
~3.4 GB
Engines
GGUF · MLX

Get it running

Llama-3.2-3B-Instruct; tool calling. GGUF + MLX. Hugging Face: meta-llama/Llama-3.2-3B-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)

  • None in this guide — use a Mac or Connect.