Gemma · 4B · In LM Mini

Gemma 3 4B Instruct on a phone

Google’s mid-size Gemma 3 — sharper answers; some builds can look at images.

Parameters
4B
Typical Q4
~2.7–3.7 GB
RAM to budget
~4.2 GB
Engines
GGUF · MLX

Get it running

google/gemma-3-4b-it; multimodal on supported builds. GGUF + MLX. Hugging Face: google/gemma-3-4b-it.

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)