Gemma · 9B · Desktop / import

Gemma 2 9B Instruct on a phone

Google’s 9B chat model — polished answers when you have Mac RAM or a GPU.

Parameters
9B
Typical Q4
~5.4 GB (Q4)
RAM to budget
~8.2 GB
Engines
GGUF · MLX

Get it running

Gemma-2-9B-IT; still excellent instruction following. Hugging Face: google/gemma-2-9b-it.

Load in LM Studio or Ollama, then chat from the phone.

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)