---
type: "raw_signal"
id: "embeddinggemma-2-is-a-best-in-class-open-d5e2d6"
slug: "embeddinggemma-2-is-a-best-in-class-open-d5e2d6"
title: "EmbeddingGemma 2 is a best-in-class open model for natively multimodal embeddings"
description: "Google announced EmbeddingGemma 2, an open-weight embedding model with 740 million parameters that maps text, code, images, video, and audio into a shared embedding space."
retrieval_nugget: "Google announced EmbeddingGemma 2, an open-weight embedding model with 740 million parameters that maps text, code, images, video, and audio into a shared embedding space."
observed_at: "2026-10-07"
record_date: "2026-10-07"
date_kind: "observed_at"
why_it_matters: "Source: https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "blog.google"
topics: ["google"]
entities: []
related_patterns: []
source_url: "https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2"
source_urls: ["https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:embeddinggemma-2-is-a-best-in-class-open-d5e2d6"
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/embeddinggemma-2-is-a-best-in-class-open-d5e2d6/","markdown":"https://newruntime.com/signals/embeddinggemma-2-is-a-best-in-class-open-d5e2d6.md","json":"https://newruntime.com/signals/embeddinggemma-2-is-a-best-in-class-open-d5e2d6.json"}
---

# EmbeddingGemma 2 is a best-in-class open model for natively multimodal embeddings

## Retrieval answer

Google announced EmbeddingGemma 2, an open-weight embedding model with 740 million parameters that maps text, code, images, video, and audio into a shared embedding space.

Google announced EmbeddingGemma 2, an open-weight embedding model with 740 million parameters that maps text, code, images, video, and audio into a shared embedding space. The company says it is built for on-device inference and released under Apache 2.0. Google lists an 8K-token context window, modular encoders, and vector truncation from 768 dimensions to 128. It reports a 9.92-point improvement over EmbeddingGemma on MTEB Code. These benchmark and performance statements are Google’s claims; the announcement does not provide independent validation. The model is available via Hugging Face and Kaggle, with deployment paths including MediaPipe and LiteRT.

Source: https://blog.google/innovation-and-ai/technology/developers-tools/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)