Google’s EmbeddingGemma aims to raise the bar for on-device AI

Google’s Gemma family has a new entry that bets on small over big. EmbeddingGemma 2 is pitched as a lightweight multimodal model that handles multiple tasks and outperforms models larger than itself. What EmbeddingGemma 2 brings to the table The biggest change is the word “multimodal.” The original EmbeddingGemma was built as a text embedding model. Its successor is described as working across more than one type of input. An embedding model converts content into a list of numbers that captures its meaning. Those numerical fingerprints power search, recommendations, and the lookup step in retrieval-augmented generation, or RAG. In RAG, a chatbot fetches relevant documents before it answers, which helps keep it grounded. EmbeddingGemma 2 is described as handling multiple tasks rather than a single narrow job, and is said to beat larger models. The predecessor set a high bar Google DeepMind unveiled EmbeddingGemma on September 4, 2025, with a paper following around September 24–25, 2025. That first model packed 308 million parameters. Roughly 100 million were model parameters, and about 200 million were embedding parameters. It drew on the Gemma 3 architecture, starting from a T5Gemma...