Technology

Gemma 3n

Gemma 3n is Google DeepMind's open, multimodal AI model: engineered for lightning-fast, privacy-first performance on mobile devices and laptops.

Gemma 3n delivers state-of-the-art multimodal AI (audio, text, image, video) directly to your device. Built on a groundbreaking architecture shared with the next-gen Gemini Nano, it is optimized for speed and efficiency. Key innovations like Per-Layer Embeddings (PLE) allow the 5B and 8B models to run with a dynamic memory footprint comparable to 2GB and 4GB, enabling advanced, offline-ready features on consumer hardware. This is the foundation for a new wave of highly capable, on-the-go applications.

https://ai.google.dev/gemma

What builders pair with Gemma 3n

Projects using both technologies. Select a pairing to see a project.

Built with Gemma 3n

Android 1 shared project Dart 1 shared project Flutter 1 shared project GeckoEmbeddingModel 1 shared project image input 1 shared project Markwon 1 shared project

6 more pairings

MediaPipe GenAI 1 shared project Node 1 shared project On-device multimodal AI 1 shared project PostgreSQL 1 shared project RAG 1 shared project React 1 shared project

Pairing: Android

Photo from the event — Event photo

Offline AI Tutor on Android: Gemma 3n + MediaPipe GenAI with Local RAG+CAG implementation

Seattle · September 30, 2025

view project | view Android

Recent Talks & Demos

Showing 1-3 of 3

Members-Only

Sign in to see who built these projects

Sign in View FAQ

PalliAssist: Transforming Palliative Care with Compassionate AI

MenuMind: On-Device AI for Menu Translation and Allergen Awareness

Gemma 3n: Offline Android RAG

Android MediaPipe GenAI