Introducing EmbeddingGemma: The Best-in-Class Open Model for On-Device Embeddings

Discover EmbeddingGemma, a state-of-the-art 308 million parameter text embedding model designed to power generative AI experiences directly on your hardware. Ideal for mobile-first Al, EmbeddingGemma brings powerful capabilities to your applications, enabling features like semantic search, information retrieval, and custom classification – all while running efficiently on-device. In this video, Alice Lisak and Lucas Gonzalez from the Gemma team introduce EmbeddingGemma and explain how it works. Learn how you can run this model on less than 200MB of RAM with quantization, customize its output dimensions with Matryoshka Representation Learning (MRL), and build powerful offline Al features. Resources: Learn about EmbeddingGemma → https://developers.googleblog.com/en/introducing-embeddinggemma EmbeddingGemma documentation → https://ai.google.dev/gemma/docs/embeddinggemma Gemma Cookbook → https://github.com/google-gemini/gemma-cookbook Quickstart RAG notebook → https://github.com/google-gemini/gemma-cookbook/blob/main/Gemma/%5BGemma_3%5DRAG_with_EmbeddingGemma.ipynb Discover Gemma models → https://deepmind.google/models/gemma Chapters 0:00 - Intro 0:26 - Model overview 1:18 - Model features 2:29 - RAG 2:54 - Website embedding demo 3:23 - Tools and platforms 3:41 - Conclusion Subscribe to Google for Developers → https://goo.gle/developers Speaker:Alice Lisak Lucas Gonzalez Products Mentioned: Google AI, Gemma,Generative AI

Channel: Google for DevelopersGenerated by anonymousDuration: 4mPublished Sep 04, 2025
Thumbnail for Introducing EmbeddingGemma: The Best-in-Class Open Model for On-Device Embeddings ▶ Watch on YouTube

Video Chapters

Original Output

0:00 Discover EmbeddingGemma: A new era of mobile AI
0:25 Unveiling the power: 300 million parameters strong
0:53 Tiny yet mighty: Only 300MB RAM footprint
1:19 Practical magic: Semantic search & information retrieval
1:40 Top-tier performance: Best-in-class MTEB scores
2:03 Your data, your rules: On-device privacy & offline mode
2:29 Next-gen AI: Empowering RAG on mobile
2:54 See it in action: Personalized search demo
3:23 Seamless integration: Customize across platforms
3:40 Get started now: Open, fast, and ready to deploy

Timestamps by StampBot 🤖