# Google DeepMind introduces EmbeddingGemma 2 for on-device multimodal embeddings

Google DeepMind has introduced EmbeddingGemma 2, its first natively multimodal open model for on-device embeddings that unifies text, code, images, audio, and video in a shared space.

Language: en
Time zone: America/Los_Angeles

HTML: https://didcodexreset.com/news/216df868166b44c199844499.html

Content language: en
Localization state: sameLanguage

Source: Google DeepMind · Published 10/6/2026, 09:26:32

Google DeepMind has introduced EmbeddingGemma 2, its first natively multimodal open model designed for on-device embeddings.

The model expands beyond text representations to unify code, images, audio, and video within a shared embedding space.

Tags: Google DeepMind, EmbeddingGemma 2, Multimodal, Embeddings

[View original post](https://x.com/GoogleDeepMind/status/2107502286758895878)