NEW: EmbeddingGemma 2 just released on Hugging Face. Project text, images, video, and audio into a single, unified embedding space. At just 740M parameters, it can even run 100% locally in your browser on WebGPU with 🤗 Transformers.js! Try it yourself 👇

Introducing EmbeddingGemma 2, our new open embeddings model for on-device use cases! 👀 Code, image, video, audio, and text embeddings 🤏 Modular, going from 270m to 740m parameters 🪆 Matryoshka embeddings for storage efficiency 🤗 Apache 2 License

Introducing EmbeddingGemma 2, a new open multimodal model that sets the standard for on-device efficiency. - our first open, natively multimodal embedding model - handles text, code, image, video, and audio tasks within a lightweight, modular 740M parameter form factor - ideal for offline, privacy-first RAG when paired with Gemma 4 - outperforms some specialist models more than twice its size Weights available now on Hugging Face.

Google releases EmbeddingGemma 2, a lightweight multimodal embedding model built for private, on-device search and retrieval.📜 Apache 2.0. 🤖 🏆 Delivers leading quality among sub-1B multimodal embedding models, including a 9.92-point gain over EmbeddingGemma 1 on MTEB Code. 🔎 Maps text, code, images, video, and audio into one shared space, enabling searches such as finding a video moment from a voice memo or searching audio with text. 📱 The 740M model uses as little as ~191MB active RAM for quantized text-only weights and ~567MB for the full multimodal model on a Pixel 11 Pro. 📦 Matryoshka embeddings shrink from 768d to 128d, reducing vector storage by up to 6×. 📚 Its 8K context handles up to 5.5 minutes of audio, 29 images, 58 video frames, or interleaved multimodal inputs.

BREAKING: Google launches EmbeddingGemma 2, a 740 million parameter open model embedding code, images, video and audio entirely on device. Allowing personal agents to run more AI inference on phones, laptops and glasses instead of the cloud.

Google released EmbeddingGemma 2 open weight model under Apache 2 license! > “Our lightweight, multimodal embedding model maps text, code, images, video, and audio into a single, unified embedding space.“ > 740M parameter form factor with modular encoders and 8K context window. Embedded testing time 👀

$GOOGL just released EmbeddingGemma 2 which is a 740M parameter open model that handles code, images, video & audio entirely on device. That pushes more AI from cloud onto phones, laptops & glasses as personal agents become more private & always on.

We’re releasing EmbeddingGemma 2, our first natively multimodal open model engineered for on-device embeddings. Built on the Gemma 4 architecture and released under an Apache 2.0 license, it goes beyond text to unify images, video, audio, and code in a single embedding space.

Today at 12:00pm, don't miss our live demonstration on EmbeddingGemma 2 at the @COLM_conf Google booth (#107#). Connect with Sahil Dua and explore an open multimodal model that unifies text, images, audio, and video representations. #COLM2026# @GoogleDeepMind

It’s Friday 🎉 Here’s a look at this week’s announcements: — is now available globally in English, allowing anyone to use our detector portal to easily verify if images, video, or audio files were AI-generated by Google or industry partners — Nano Banana 2.1, featuring leaps in visual design, subject consistency, and precise spot editing that lets you change specific details without altering the whole image — EmbeddingGemma 2, our first natively multimodal open model that unifies text, images, video, audio, and code into a single space for on-device embeddings — @GoogleGemma 4 paired with BOTANIC-1, a specialized AI trained on plant DNA, to rapidly pinpoint the exact mutations that make crops thrive — Gemini agent for your business, a universal cloud agent running 24/7 to get your work done — Guided Vision in Gemini Live, offering real-time visual assistance and dynamic audio descriptions via your camera, built alongside the blind and low-vision community