Gemma · 2.3B · Desktop / import

Gemma 4 E2B Instruct on a phone

Google’s 2026 edge Gemma — ~2.3B effective, text + image + audio. The new tiny phone default if your engine supports Gemma 4.

Parameters
2.3B
Typical Q4
~1.4–1.8 GB (Q4/QAT)
RAM to budget
~2.9 GB
Engines
GGUF

Get it running

google/gemma-4-E2B-it (Apr 2026). Official QAT GGUF. Apache 2.0. ~5.1B with embeddings; plan ~2–3 GB live. Hugging Face: google/gemma-4-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)