← Friday, October 9, 2026Models & trainingRelease

EmbeddingGemma 2 brings text, image, audio, and video into one embedding space

deepmind.google 4 min read Editor score 6/10

Google DeepMind says the lightweight model maps combinations of text, images, audio, and video into a unified embedding space for on-device use. Engineers building local search or retrieval systems should watch for the model’s capabilities and deployment trade-offs.

What

- EmbeddingGemma 2 is an open, 740-million-parameter model that maps text, images, audio, and video into a shared embedding space.

How

- Optional vision and audio encoders add multimodal support to a text-only configuration; Matryoshka learning lets developers truncate output vectors.

Why it matters

- Shared embeddings support on-device multimodal search and retrieval, including searching audio with text or finding a video clip from a voice memo.

Read on deepmind.google →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.