# Google releases EmbeddingGemma 2, a 740-million-parameter open embedder for text, code, images and audio under Apache 2.0

Google reports that the text-only configuration runs in about 191 MB of active memory on a quantized Pixel 11 Pro, and that its score on the Massive Text Embedding Benchmark's code track rose nearly 10 points over the first version.

- Published: 2026-10-08T06:25:29.519Z
- Canonical: https://polylog.news/ai/2026-10-08/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/), [AI Weekly](https://aiweekly.co/alerts/google-ships-embeddinggemma-2-740m-multimodal-embedder-apache-20), [Pasquale Pillitteri](https://pasqualepillitteri.it/en/news/21252/embeddinggemma-2-google-open-multimodal-embeddings)

Google has released EmbeddingGemma 2, an open embedding model that maps text, code, images, video frames and audio into one vector space. AI Weekly reports that it has 740 million parameters and ships under the Apache 2.0 license. The desig…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-08/google-releases-embeddinggemma-2-a-740-million-parameter-ope (subscription information: https://polylog.news/pricing).