Gemma · 2B · Desktop / import

Gemma 3n E2B on a phone

Google’s on-device Gemma 3n (effective 2B). Built for phones, including audio-aware builds.

Parameters
2B
Typical Q4
~1.5 GB
RAM to budget
~2.8 GB
Engines
GGUF

Get it running

google/gemma-3n-E2B-it. LiteRT / GGUF community quants. Newer than Gemma 3 1B. Hugging Face: google/gemma-3n-E2B-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)