Model release · Google

EmbeddingGemma 2

Model released

Oct 06, 2026 · Date only

Review updated

Oct 07, 2026 06:32 Wed · Beijing Time (UTC+8)

EmbeddingGemma 2 is a 740-million-parameter multimodal embedding model released under Apache 2.0, with weights available on Hugging Face and Kaggle. It maps text, code, images, audio and video into a shared embedding space for on-device search. Google says it can be paired with Gemma 4 for private, on-device retrieval-augmented generation.