AI Matters
Why it matters
Google releases EmbeddingGemma 2, a small open model for search and retrieval
The Decoder Google claims EmbeddingGemma 2 outperforms rival embedding models twice its size
Google released EmbeddingGemma 2, an open 740 million parameter model that handles text, images, video, audio, and code and needs about 191 MB of RAM.
Why it matters
Apps can search across text, images, video, and audio on your own device, without sending data to the cloud.
Latest brief · Oct 19, 2026