Gemma · 4B · Desktop / import

Gemma 3n E4B on a phone

Gemma 3n effective-4B — Google’s newer on-device stack, including multimodal 3n builds.

Parameters
4B
Typical Q4
~2.6 GB (Q4)
RAM to budget
~4 GB
Engines
GGUF

Get it running

google/gemma-3n-E4B-it. Community GGUF (bartowski). Heavier than E2B. Hugging Face: google/gemma-3n-E4B-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)