Gemma 3n is Google's new open model, optimized for on-device multimodal AI. Its novel MatFormer architecture enables powerful yet efficient models (like the 2B/4B variants) that can run locally on phones and laptops. Supports image, audio & video.

Gemma 3 is Google's new models for multimodal AI (text, images, video). 1B-27B sizes, 128K context, 140+ languages. Includes ShieldGemma 2 for safety.

A family of lightweight, state-of-the art open models built from the same research and technology used to create the Gemini models

It is a mobile application, it is based on the visual description of any image you upload, Gemini's AI uses the image you give it and describes, interprets or advises what you can ask.