# EmbeddingGemma 2



Google



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.

- Model released: Oct 06, 2026 · Date only
- Review updated: Oct 07, 2026 06:32 Wed · Beijing Time (UTC+8)

## Sources

- Source archive: https://x.com/GoogleDeepMind/status/2107502286758895878
- Source archive: https://x.com/GoogleDeepMind/status/2107502289652982118

Canonical entry: https://www.ailyre.com/source/?id=google-deepmind-embeddinggemma-2&lang=en