Google launches EmbeddingGemma 2 for on-device multimodal search

October 6, 2026

Google released EmbeddingGemma 2 on October 6, extending its embedding model from text to code, images, audio and video. The 740-million-parameter model uses the Gemma 4 architecture and is available under an Apache 2.0 license.

Embeddings represent information in a form that software can compare for similarity. Google describes uses such as finding a video moment from a voice query or locating audio recordings through text, with processing on local hardware.

The model has an 8,000-token context window and optional vision and audio components. Google says a text-only configuration uses 270 million parameters.

Local retrieval, with deployment choices

Google lists weights on Hugging Face and Kaggle, plus support through its AI Edge tools. Its published memory figures depend on quantization and the tested Pixel 11 Pro configuration; they are not universal requirements for every device. Model Garden availability is described as coming soon.

Sources

Google DeepMind announcement, October 6, 2026

Feature image: AI-generated editorial illustration for Guava Insights. Conceptual artwork, not a product photograph or depiction of an actual facility.

Topics:
Read next
November 14, 2026

How to Set Up an Encrypted Time Machine Backup on Mac

Set up an encrypted external Time Machine backup, check completion, practise restoring a file, and understand local snapshots, exclusions, and recovery limits.
November 13, 2026

NVIDIA Leadership Shock Puts AI Infrastructure to the Test

NVIDIA’s abrupt CEO transition puts leadership, execution and customer confidence at the centre of the AI infrastructure boom just days before its next earnings report.
November 11, 2026

CoreWeave’s AI Cloud Growth Accelerates as 2026 Capital Spending Climbs to $39 Billion

CoreWeave raised its 2026 revenue forecast after third-quarter revenue reached US$3.661 billion, but capital spending and financing costs show the risks behind the AI cloud buildout.