Home / Models / Gemma 4 E2B

Gemma 4 E2B

Maker: Google · language

The smallest open Gemma 4 model: 2.3B effective parameters (5.1B with embeddings). Text, image and audio in, text out. 128K context, designed for on-device use.

Открытые веса под Apache 2.0. Доступна в Vertex AI Model Garden.

Understands

text, images, audio

Produces

text, code

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.