EmbeddingGemma 2

EmbeddingGemma 2

An open, lightweight multimodal embedding model.

Google DeepMind's open multimodal embedding model mapping text, images, video and audio into one 768-dim space for on-device use.

Hugging Face model page

Hugging Face model page

1 / 3

Overview

What is EmbeddingGemma 2?

An open, lightweight multimodal embedding model.

EmbeddingGemma 2 is Google DeepMind's open multimodal embedding model that maps text (including code), images, video and audio into one shared 768-dimensional embedding space, so developers can run cross-modal retrieval in a single model. At about 740M total parameters it is built for on-device use: each encoder can be loaded selectively (the default full set is around 300M), and it runs on consumer hardware like phones and laptops with low latency. Matryoshka (MRL) training supports 128/256/512/768-dimensional embeddings, cutting vector storage up to 6x. An 8K-token context window covers long documents for RAG, task-specific instruction prefixes steer representations toward search, classification, clustering or similarity, and it understands 100+ languages with stronger code-task performance than its predecessor. It is fully open under Apache 2.0 — free to download, deploy and use commercially — and works with sentence-transformers, Hugging Face Transformers, Transformers.js and the HF Inference API. Made for developers and app builders who need lightweight, on-device multimodal embeddings for search, retrieval-augmented generation, recommendations, classification and clustering.

Platforms and languages

EmbeddingGemma 2 Availability

Platforms

ApiWeb

Languages

English

Capabilities

EmbeddingGemma 2 Key Features

Native multimodality

Map text (including code), images, video and audio into one shared 768-dimensional embedding space for cross-modal retrieval.

Multilinguality and code

Understand 100+ languages and perform code tasks about 14% better than its predecessor.

Flexible on-device footprint

740M total parameters with selectively loadable encoders; the default full set is about 300M, designed for phones, laptops and other consumer hardware.

Elastic embedding dimensions

Matryoshka (MRL) support for 128/256/512/768-dimensional embeddings, reducing vector storage up to 6x with minimal quality loss.

8K context with task steering

8K-token context window for long-document retrieval and RAG, with task-specific instruction prefixes that steer embeddings toward search, classification, clustering or similarity.

Best for

Who uses EmbeddingGemma 2?

Developers and app builders needing lightweight multimodal embeddings

Build search, RAG, recommendation, classification and clustering features that run on-device

Plans and access

EmbeddingGemma 2 Pricing

Free

Free: open weights under Apache 2.0, download and use commercially at no cost.

Free trial available

Common questions

EmbeddingGemma 2 FAQs

Is it free and can I use it commercially?

Yes. It is released under Apache 2.0, so you can download the weights and use them commercially at no cost.

Can I run it on-device or locally?

Yes. It is designed for consumer hardware: you can load only the encoders you need, and the default full configuration is about 300M parameters, suitable for phones and laptops.

Which modalities does it support?

Text (including code), images, video and audio — all mapped into one shared 768-dimensional embedding space for cross-modal search.

How do I use the model?

Through sentence-transformers, Hugging Face Transformers, Transformers.js, or the HF Inference API.

Reviews

See what the community thinks and share your experience.

—

Based on 0 ratings

Rating distribution

0
0
0
0
0

Leave a review

Sign in to rate

Community reviews

No reviews

No written reviews yet.

Explore by category

Llms Foundation Models

View all Llms Foundation Models websites
GLM-5.3 preview
GLM-5.3

Z.ai's flagship open-weight reasoning model for coding agents and long-horizon tasks, with a 1M-token context window.

Llms Foundation Models
Qwen4-Max preview
Qwen4-Max

Alibaba's flagship 2.4T-parameter model with a 1M-token context and native vision, priced from $1.50 per million input tokens.

Llms Foundation Models

Explore by category

AI Apis Sdks

View all AI Apis Sdks websites
AI Gateway preview
AI Gateway

A cloud AI agent that handles research, code, files, and media from one prompt, across 200+ models.

AI Apis Sdks
Memanto Cloud preview
Memanto Cloud

Long-term memory for AI agents: it remembers, resolves conflicts, and briefs agents before they act.

AI Apis Sdks
TTAPI preview
TTAPI

Access Midjourney, Flux, Wan 3.0, Suno, GPT, Claude, Gemini, Grok, and 100+ AI models through one unified REST API. One API key, one balance, pay as you go.

AI Apis Sdks
Gridline preview
Gridline

Fine-tune, distill, and run batch inference on open models through one OpenAI-compatible API.

AI Apis Sdks
Mesh API preview
Mesh API

One token-efficient gateway to 1,000+ AI models, with pay-as-you-go pricing and no subscription.

AI Apis Sdks

Explore by category

AI Search Discovery

View all AI Search Discovery websites
Counter clicker preview
Counter clicker

Counter Clicker is a free online tool to count people, track scores, monitor inventory, and manage daily tasks with simple, easy-to-use controls.

AI Search Discovery