# EmbeddingGemma 2 operates on 191MB to 567MB of RAM with an 8K context window

Google detailed operational specifications for EmbeddingGemma 2, stating the 740M model uses between ~191MB and 567MB of active RAM, expands its context window to 8K, and processes up to 5.5 minutes of audio, 29 images, or 58 video frames per pass.

Language: en
Time zone: America/Los_Angeles

HTML: https://didcodexreset.com/news/0d40d3fe2f6d49d7b408d653.html

Content language: en
Localization state: sameLanguage

Source: Google · Published 10/6/2026, 09:35:33

The 740-million-parameter EmbeddingGemma 2 operates with active RAM usage between approximately 191MB and 567MB. According to Google, the model outperforms some models more than twice its size.

EmbeddingGemma 2 also features an 8K context window, representing a fourfold increase over the first generation. In a single pass, it can process up to 5.5 minutes of audio, 29 images, or 58 video frames.

Tags: EmbeddingGemma, Google, On-Device AI, Multimodal AI

[View original post](https://x.com/Google/status/2107505123941376129)