---
type: "raw_signal"
id: "google-released-embeddinggemma-2-a-740m-open-weight-79a128"
slug: "google-released-embeddinggemma-2-a-740m-open-weight-79a128"
title: "Google released EmbeddingGemma 2 , a 740M open-weight multimodal embedding model for text, image, audio, and video."
description: "Google announced EmbeddingGemma 2, an open-weight multimodal embedding model with 740 million parameters."
retrieval_nugget: "Google announced EmbeddingGemma 2, an open-weight multimodal embedding model with 740 million parameters."
observed_at: "2026-10-21"
record_date: "2026-10-21"
date_kind: "observed_at"
why_it_matters: "Source: https://developers.googleblog.com/google-ai-edge-with-embeddinggemma-2"
novelty: "notable"
verification_level: "source-linked"
signal_type: "update"
source_platform: "developers.googleblog.com"
topics: ["google"]
entities: ["Google","Google DeepMind","EmbeddingGemma 2","Google AI Edge Gallery","ML Kit","MediaPipe Tasks"]
related_patterns: ["generative-media-becomes-application-infrastructure"]
novelty_label: "same_event"
what_changed: "Same event as EmbeddingGemma 2 is a best-in-class open model for natively multimodal embeddings"
prior_refs: ["memory:85ed9687-711c-8ec6-ab91-e7d068a6140b","memory:f6a403c1-0a1d-8a80-aceb-e16156b205d8","memory:791720d9-7f8f-8ad4-aa88-7902a9635a88","memory:36af579f-450e-8708-ac02-37aab05df9dd","memory:d1a45460-adac-83d6-ab8c-bf369ee9f9be","memory:77662b20-4cce-83f3-aa62-7f322da210f1","memory:a94cb415-188e-81bc-ad08-88d6060e5e13"]
source_url: "https://developers.googleblog.com/google-ai-edge-with-embeddinggemma-2"
source_urls: ["https://developers.googleblog.com/google-ai-edge-with-embeddinggemma-2"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:google-released-embeddinggemma-2-a-740m-open-weight-79a128"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/google-released-embeddinggemma-2-a-740m-open-weight-79a128/","markdown":"https://newruntime.com/signals/google-released-embeddinggemma-2-a-740m-open-weight-79a128.md","json":"https://newruntime.com/signals/google-released-embeddinggemma-2-a-740m-open-weight-79a128.json"}
---

# Google released EmbeddingGemma 2 , a 740M open-weight multimodal embedding model for text, image, audio, and video.

## Retrieval answer

Google announced EmbeddingGemma 2, an open-weight multimodal embedding model with 740 million parameters.

Google announced EmbeddingGemma 2, an open-weight multimodal embedding model with 740 million parameters. The model maps text, images, video frames, and audio into a shared vector space and is designed for local execution. Google says the full multimodal model uses about 567 MB of active RAM on a Pixel 11 Pro, while text-only weights use about 191 MB.

The Google AI Edge Gallery adds demonstrations for searching local photos and videos with natural-language queries, including locating moments in video without first transcribing audio or generating text captions. Google also says ML Kit support is planned for the coming weeks; that integration is not yet available according to the announcement.

Source: https://developers.googleblog.com/google-ai-edge-with-embeddinggemma-2

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Google](https://newruntime.com/topics/google.md): Explore the google topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)