Gemma · 4.5B · Desktop / import

Gemma 4 E4B Instruct on a phone

Google’s on-device Gemma 4 (~4.5B effective) with image and audio. The 2026 upgrade from Gemma 3 4B / 3n E4B.

Parameters
4.5B
Typical Q4
~2.6–3.2 GB (Q4/QAT)
RAM to budget
~4.4 GB
Engines
GGUF

Get it running

google/gemma-4-E4B-it. Official QAT GGUF. ~8B with embeddings; budget ~4 GB live. Apache 2.0. Hugging Face: google/gemma-4-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)