Author
Google Context128k
Gemma 4 E2B is the smallest model in Google DeepMind's Gemma 4 family of open models, with 2.3B effective parameters (5.1B with embeddings), designed for efficient local execution on phones and laptops. It is a configurable reasoner with native function calling and system-prompt support, handles text and image input, returns text, and has a 128K-token context window.