Google claims EmbeddingGemma 2 outperforms rival embedding models twice its size

Google has released EmbeddingGemma 2, an open model with 740 million parameters that converts text, images, video, audio, and code into vectors. The model runs on-device, requires about 191 MB of RAM, and reportedly outperforms some competing models twice its size. When paired with a small open model like Gemma 4, it can run offline RAG apps without sending data to external servers.