Skip to main content

News · Development · AI

Google DeepMind announces EmbeddingGemma 2, an open multimodal embedding model

Google DeepMind released EmbeddingGemma 2 on Oct 6, an open-source model unifying text, code, image, video and audio embeddings for on-device use.

1 min read Source: blog.google

Audio summary 0:16

Headline and summary, read by a synthetic voice.

What changed: Google DeepMind introduced EmbeddingGemma 2, which natively maps text, code, images, video and audio into a unified embedding space. Built on the Gemma 4 architecture and released under the Apache 2.0 license, the model has 740 million parameters, improved MTEB Code score from 68.76 to 78.68 (a 9.92-point gain), and extended its context window to 8K tokens, 4x larger than EmbeddingGemma 1.

Who is affected

The source names developers and integration partners (Hugging Face, Kaggle, Qdrant, Ollama, LMStudio among others); no specific country or sector restriction is stated.

What it means for your business

For businesses building on-device search or RAG pipelines, this means a new open-source model, released under the Apache 2.0 license, that can now process image, audio and video alongside text in a single download.

What to watch

No action is required right now. Businesses using AI for product search, support, or content matching can have their technical teams evaluate the model's fit for their own infrastructure.

Timing

The model was announced on October 6, 2026 and is downloadable via Hugging Face and Kaggle; the source gives no separate effective date.

Source: https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2/

Primary source

blog.google

This news item is compiled from the primary source listed.

This item reports a development; it does not require any action from your business today.

All articles

Related reading

First conversation

Tell us what you want to do, and we will work out together where to start.

In the first call we talk through your business, where things stand and what matters most. We say plainly which parts make sense for us to take on and which you should run yourself.

Cookie preferences

We use measurement and advertising tools (Google Analytics, Microsoft Clarity, Google Ads, Meta Pixel) to improve the site and measure the results of our ads, only with your consent. Necessary records are always on. Details in our cookie policy.