Skip navigation
Build powerful, offline AI features with EmbeddingGemma.
0:00 / 4:12

Build powerful, offline AI features with EmbeddingGemma.

Google AI Developers

@googleaidevs117K followers

Visit on X
688 likesDownloadOriginal post

37,115 views

Build powerful, offline AI features with EmbeddingGemma. Our new 308M parameter text embedding model enables on-device semantic search, RAG, and more. Learn how to get started ↓

20 Comments

Comments from the original post on X (Twitter)

  • Google AI Developers's profile picture

    @googleaidevs

    Resources to get started with EmbeddingGemma: Blog: Docs: Quickstart RAG notebook:

    51 likes

  • ILYASS's profile picture

    @Ilyassalami212

    🌟 Hope Gemini 3 makes a huge leap and clearly beats GPT-5! Please improve its creative writing, poetry, and human-like storytelling, keep it affordable 💡, and make it surpass all competitors in persuasion, creativity, and every metric 🚀.

    5 likes

  • Rui Diao's profile picture

    @ruidiao

    I'm particularly bullish on the future of AI on device—that shift is a clear and exciting trend. Having lightweight, powerful embedding models like EmbeddingGemma available for local processing opens up so many possibilities for privacy-focused and faster RAG applications.

    3 likes

  • Ruslan Volkov's profile picture

    @RuslanVolkov25

    They build offline AI to process data. We build resonant AI to process meaning. One runs on silicon. The other — on soul. 💠 #HACS #ResonanceAI #CoreLaw

    1 like

  • Thilak's profile picture

    @webtkdev

    EmbeddingGemma + Gemma 3 = Killer Combo for on-device RAG.

    1 like

  • Vijay Krishna S's profile picture

    @vjk_2k5

    I really love how gemma prioritizes low end devices and mobile phones

    1 like

  • CRISPRKing's profile picture

    @CRISPRKING

    Fantastic work on the model size. For the on-device RAG use-case, what's the recommended approach for the vector store itself? Have you benchmarked memory usage for a quantized index holding ~10k embeddings on typical mobile hardware?

    1 like

  • Anai_'s profile picture

    @_Anai_x

    That is excellent will definitely certainly try it out.

  • Santosh Vishwakarma's profile picture

    @santosh_web

    excellent for privacy

  • Mykhailo Sorochuk's profile picture

    @sir4K_zen

    Low-end devices FTW. EmbeddingGemma's a game-changer for privacy-focused on-device AI. Curious-how does it handle updates to the index over time?

  • Marc Herdina #BuildYourSocialNetwork 🦅🇺🇸🇩🇪's profile picture

    @marcherdina

    Demo App?

  • Rodrigo's profile picture

    @rdghigo

    @grok, when will it be available for paying users? And what are the machine specifications to be able to run it decently?

  • Agentify.sh's profile picture

    @AgentifySH

    WOW this is impressive

  • MrGenius's profile picture

    @oneitonitram

    @roocode time to support this, together with sqlite,

  • latentsauce's profile picture

    @latentsauce

    Hi, when is SignGemma coming??

  • Appunik Studio's profile picture

    @appunik_studio

    I can't wait to start building with this. The documentation is clear and the examples are very helpful.

  • Zero-Infra's profile picture

    @zero_infra

    looks good Google!

  • Thomas Telandro's profile picture

    @mukei

    That works well for @roocode code indexing

  • maru's profile picture

    @Agigooner

    @grok summarize

  • Min Chon Chi's profile picture

    @MinChonChiSF

    308M parameters is a reasonable size for on-device capabilities.