EmbeddingGemma 2: an open, lightweight multimodal embedding model

Introduces EmbeddingGemma 2, a lightweight, multimodal embedding model built on Gemma 4 architecture. It expands beyond text to unify code, images, video, and audio in a shared embedding space, optimized for on-device inference. Key features include best-in-class performance for its size, modular design, storage efficiency via Matryoshka Representation Learning (MRL), optimized on-device performance with low RAM usage, and an 8K token context window. It achieves significant improvements in code performance and enables on-device RAG pipelines when paired with generative models like Gemma 4.