Build powerful, offline AI features with EmbeddingGemma.
@googleaidevs117K followers
37,115 views
20 Comments
Comments from the original post on X (Twitter)

@googleaidevs
Resources to get started with EmbeddingGemma: Blog: Docs: Quickstart RAG notebook:
51 likes

@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

@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

@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

@webtkdev
EmbeddingGemma + Gemma 3 = Killer Combo for on-device RAG.
1 like

@vjk_2k5
I really love how gemma prioritizes low end devices and mobile phones
1 like

@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_x
That is excellent will definitely certainly try it out.

@santosh_web
excellent for privacy

@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?

@marcherdina
Demo App?

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

@AgentifySH
WOW this is impressive

@oneitonitram
@roocode time to support this, together with sqlite,

@latentsauce
Hi, when is SignGemma coming??

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

@zero_infra
looks good Google!

@mukei
That works well for @roocode code indexing

@Agigooner
@grok summarize

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