Introduction to On-Device AI
The rapid expansion of generative AI has changed the way Google and other tech giants design products. Most AI features are running on remote servers with a ton of processing power. However, your phone has a lot less power. Google appears poised to give developers some important new mobile AI tools. At I/O, Google will likely announce a new set of APIs to let developers leverage the capabilities of Gemini Nano for on-device AI.
What is Gemini Nano?
Google has quietly published documentation on big new AI features for developers. According to Android Authority, an update to the ML Kit SDK will add API support for on-device generative AI features via Gemini Nano. It’s built on AI Core, similar to the experimental Edge AI SDK, but it plugs into an existing model with a set of predefined features that should be easy for developers to implement.
Features of Gemini Nano
Google says ML Kit’s GenAI APIs will enable apps to do summarization, proofreading, rewriting, and image description without sending data to the cloud. However, Gemini Nano doesn’t have as much power as the cloud-based version, so expect some limitations. For example, Google notes that summaries can only have a maximum of three bullet points, and image descriptions will only be available in English. The quality of outputs could also vary based on the version of Gemini Nano on a phone.
Versions of Gemini Nano
The standard version (Gemini Nano XS) is about 100MB in size, but Gemini Nano XXS, as seen on the Pixel 9a, is a quarter of the size. It’s text-only and has a much smaller context window. Not all versions of Gemini Nano are created equal, as shown in the image below.
Credit: Ryan Whitwam
Impact on Android
This move is good for Android in general because ML Kit works on devices outside Google’s Pixel line. While Pixel devices use Gemini Nano extensively, several other phones are already designed to run this model, including the OnePlus 13, Samsung Galaxy S25, and Xiaomi 15. As more phones add support for Google’s AI model, developers will be able to target those devices with generative AI features.
Conclusion
Google’s introduction of Gemini Nano and the new ML Kit SDK is a significant step forward for on-device AI. With the ability to perform tasks like summarization, proofreading, and image description without sending data to the cloud, developers will be able to create more powerful and private apps. As more devices support Gemini Nano, we can expect to see even more innovative uses of AI on Android.
FAQs
Q: What is Gemini Nano?
A: Gemini Nano is a new AI model from Google that allows for on-device generative AI features.
Q: What features will Gemini Nano support?
A: Gemini Nano will support features like summarization, proofreading, rewriting, and image description.
Q: Will Gemini Nano work on all Android devices?
A: No, Gemini Nano will only work on devices that support the ML Kit SDK and have the necessary hardware capabilities.
Q: How big is the standard version of Gemini Nano?
A: The standard version of Gemini Nano is about 100MB in size.
Q: What is the difference between Gemini Nano XS and Gemini Nano XXS?
A: Gemini Nano XXS is a quarter of the size of Gemini Nano XS and is text-only with a smaller context window.
