Google Releases Open-Source Multimodal Embedding Model EmbeddingGemma 2
Understand the story
On October 7, 2026, The Decoder reported that Google released the open-source embedding model EmbeddingGemma 2, with 740M parameters, which converts text, images, video, audio, and code into vector representations and supports multimodal embedding tasks. Google said the model outperforms competitors twice its size on multimodal embedding benchmarks. Google DeepMind subsequently provided further first-hand details: EmbeddingGemma 2 is based on the Gemma 4 architecture, released under the Apache 2.0 license, and maps text, code, images, video, and audio into a shared embedding space. Overall, the event is still in the release stage; public information mainly comes from Google's announcements and performance claims, and no third-party independent evaluations have been reported yet.
AI overview of reporting · Updated 11 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- Google DeepMindSelectedEmbeddingGemma 2: an open, lightweight multimodal embedding model
Google DeepMind released EmbeddingGemma 2, a 740M-parameter model built on the Gemma 4 architecture under the Apache 2.0 license, mapping text, code, images, video and audio into a shared embedding space.
- The DecoderGoogle claims EmbeddingGemma 2 outperforms rival embedding models twice its size
Google has released the open embedding model EmbeddingGemma 2, which converts text, images, video, audio and code into vectors. With 740M parameters, Google says it beats rivals twice its size on multimodal embedding benchmarks.