Google releases EmbeddingGemma 2, an open multimodal embedding model for on-device use
EmbeddingGemma 2: an open, lightweight multimodal embedding model
Google DeepMind has released EmbeddingGemma 2, a 740-million-parameter embedding model that maps text, images, audio, and video into a shared space and runs on local hardware under an Apache 2.0 license. Matryoshka Representation Learning lets developers truncate output vectors from 768 dimensions to 512, 256, or 128, and the model supports an 8K-token context window. The model weights are available on Hugging Face and Kaggle, with Gemini Enterprise Agent Platform availability coming soon.
The release shows how a 740M-parameter multimodal embedder runs locally with a 768-to-128 dimension truncation option, useful for judging on-device retrieval designs.
Source: Google DeepMind · The Keyword · blog.google