# Google releases EmbeddingGemma 2, a 740 million parameter open model that embeds text, code, images, video and audio

Modular encoders let developers load only the text-and-code block, which Google says runs in about 191 megabytes of memory on a Pixel 11 Pro, and the context window grows to 8,000 tokens.

- Published: 2026-10-07T06:04:58.881Z
- Canonical: https://polylog.news/ai/2026-10-07/google-releases-embeddinggemma-2-a-740-million-parameter-ope
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Google DeepMind](https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2/), [Polylog editors](https://polylog.news)

Google on October 6 released EmbeddingGemma 2, an open embedding model that maps text, code, images, video and audio into one vector space. The model has 740 million parameters in total and ships under the Apache 2.0 license on Hugging Face…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-07/google-releases-embeddinggemma-2-a-740-million-parameter-ope (subscription information: https://polylog.news/pricing).