Add Generative AI capabilities to your Android app
summary
Gemini Nano runs on device via AI Core in Android 14 and targets small models for local GenAI, Gemini Nano (2–3B params), benefiting from LoRA fine‑tuning 100–1000 samples to reach production quality; cloud options use Gemini 1.5 Pro/Flash with a huge 1 million token context for multimodal prompts (text, image, audio, video). Function calling lets the model invoke app functions (orders, dates), Firebase/Vertex AI is the recommended production path, and Gemini integrates into Android Studio for code suggestions and multimodal editing.
AI-written summary · about
chapters (6)
- 0:00GenAI on Android intro
- 3:20Mobile GenAI constraints
- 12:35Gemini cloud inference
- 23:29Gemini API features
- 33:29Gemini in Android Studio
- 38:07Q&A
related talks
30mGenAI on Android with Gemini Nano and Firebase
41mBuild intelligent Android apps with Google's AI
21mAdd Generative AI capabilities to your Android app
10mAI in your pocket: Building intelligent Android apps
41mGen AI for Android Developers
18mLet's test Gemini, Google's AI in an Android application!
35mBuilding Androidify: an AI-powered Android experience
48mAndroid + AI: Solving Problems Smartly