Gemini Nano Experimental Access Available on Android
Article Summary
Taj Darra just announced that Google is opening Gemini Nano to all Android developers. On-device AI just became accessible for production-ready mobile apps.
Google's Product Manager Taj Darra reveals experimental access to Gemini Nano, their most efficient on-device AI model, through the AI Edge SDK via AICore. Initially available for text-to-text prompts on Pixel 9 devices, this marks a shift from limited partner access to broad developer availability.
Key Takeaways
- Nano 2 delivers 90% accuracy on paraphrasing, up from 44% in Nano 1
- AICore eliminates need to bundle AI runtimes or models in your app
- Processes prompts locally: no server calls, works offline, zero inference costs
- Best for specific tasks like proofreading and summarization, not open-ended chatbots
- Already powering Talkback accessibility and Pixel Recorder features
Gemini Nano 2 nearly doubles its predecessor's size while delivering 2x quality improvements on real-world tasks, now available to all Android developers through a simple SDK integration.
About This Article
Getting generative AI models onto mobile devices is tough because they need a lot of computing power and storage. Most developers don't have the specialized infrastructure to make this work.
Google built AICore, an Android system service that handles runtimes and models so developers don't have to ship them separately. The AI Edge SDK lets developers adjust inference settings like temperature, top K, and max output tokens to fit their needs.
Gemini Nano 2 scores 56% accuracy on MMLU benchmarks and 23% on MATH tasks, up from Nano 1's 46% and 14%. It also powers smart reply with 82% accuracy.