EmbeddingGemma 2: an open, lightweight multimodal embedding model
Google DeepMind · 7 Oct 2026, 05:57 AEST
Google DeepMind has introduced EmbeddingGemma 2, an open multimodal embedding model optimized for privacy-first use cases. This model expands beyond text to unify code, images, video, and audio in a shared embedding space.
Key facts
- 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.
- 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.
- 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.
Read aloud
Google Deep Mind has introduced EmbeddingGemma two, an open multimodal embedding model optimized for privacy-first use cases. This model expands beyond text to unify code, images, video, and audio in a shared embedding space. EmbeddingGemma two is the most capable model for on-device multimodal embeddings, natively mapping combinations of text, images, audio, and video into a unified embedding space. With more than twenty million downloads, builders have used it to power smarter on-device search tools and privacy-first retrieval augmented generation RAG pipelines. Built on the Gemma four architecture and released under a commercially permissive Apache two point zero license, EmbeddingGemma two has seven hundred forty million parameters, making it optimal for on-device inference.
Sources in this cluster
- EmbeddingGemma 2: an open, lightweight multimodal embedding model
Google DeepMind · 7 Oct 2026, 05:57 AEST