ModelsUS · United States
EmbeddingGemma 2: An Open, Lightweight Multimodal Embedding Model
blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2
Google has launched EmbeddingGemma 2, an advanced multimodal embedding model that unifies text, images, audio, and video into a shared embedding space. Built on the Gemma 4 architecture, it features 740 million parameters and is optimized for on-device inference, making it ideal for privacy-first applications. The model achieves top-tier performance across benchmarks for text, code, vision, and audio tasks, while offering modularity and storage efficiency. EmbeddingGemma 2 enables developers to build robust on-device search and retrieval systems, reducing latency and ensuring data privacy.