Llama · 1B · In LM Mini

Llama 3.2 1B Instruct on a phone

Meta’s pocket Llama — fast, tool-friendly, and solid for light chat.

Parameters
1B
Typical Q4
~700–808 MB
RAM to budget
~1.9 GB
Engines
GGUF · MLX

Get it running

Llama-3.2-1B-Instruct; tool calling. GGUF + MLX. Hugging Face: meta-llama/Llama-3.2-1B-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)