EmbeddingGemma 2 releases native multimodal embeddings built on Gemma 4
Original titleEmbeddingGemma 2 is out! Our first native multimodal embeddings built on Gemma 4 under Apache 2.0. 🤗 Embeds 100+ languages, code, images...
Google releases EmbeddingGemma 2, its first native multimodal embedding model, built on Gemma 4 under Apache 2.0.
It embeds over 100 languages, code, images, audio, and video into one vector, with an 8,192-token context and four sizes from 270M to 740M parameters.
Matryoshka output dimensions of 768, 512, 256, or 128 are supported, and the model is available in Sentence Transformers and LiteRT-LM, with a reported 14% gain on MTEB Code.
The release extends an embedding model to text, code, images, audio, and video in one vector, a useful option for retrieval systems that mix media types.
Source: Philipp Schmid · x.com