EmbeddingGemma 2: an open, lightweight text-and-image embedding model

What happened

Built on the Gemma 4 architecture and released under a commercially permissive Apache 2.0 license, EmbeddingGemma 2 has 740 million parameters, making it optimal for on-device inference. EmbeddingGemma 2: an open, lightweight multimodal embedding model Oct 06, 2026 | x.com Facebook LinkedIn Mail Copy link EmbeddingGemma 2 is the most capable model for on-device multimodal embeddings, natively mapping combinations of text, images, audio, and video into a unified embedding space.

Sahil Dua Research Engineer, Google DeepMind Henrique Schechter Vera Research Engineer, Google DeepMind Share x.com Facebook LinkedIn Mail Copy link Your browser does not support the audio element. Listen to article [[duration]] minutes This content is generated by Google AI. Google is an Internet and software company based in Mountain View, and its products and services include Google Search and Software tools.

With more than 20 million downloads, builders have used it to power smarter on-device search tools and privacy-first retrieval augmented generation (RAG) pipelines. This provides up to 6x storage reduction for local vector databases and memory usage.