Launch · Wednesday 7 October 2026 · story 2
Google launches EmbeddingGemma 2 for multimodal on-device embeddings
Google reports that EmbeddingGemma 2 is an open multimodal embedding model built on Gemma 4 for code, images, video, audio, and text. Google says it has 740 million parameters, an Apache 2.0 license, and is designed for on-device inference.
Why it matters. This gives developers a lightweight on-device model for embedding text, code, images, video, and audio in one shared space.
Read the original at deepmind.google