Android AICore is a new system service that enables access to AI foundation models that run on-device.
Using AICore, your Android app can access Gemini Nano, the smallest form of Gemini, Google's state-of-the-art foundation model on supported devices. AICore is in use by several Google products today.
This document details the benefits of AICore and Gemini Nano, outlines how AICore works, and how you can take advantage of it.
Google AI Edge SDK
Developers can access Gemini Nano using the Google AI Edge SDK, which provides APIs to:
- Determine if the underlying Android-powered device is supported
- Get access to Gemini Nano model
- Run inference at high performance and implement fallbacks
To learn more about this SDK, check out the developer documentation.
APIs for using AICore to run Gemini Nano are provided as part of the Google AI Edge SDK. This SDK is available under Early Access Preview (EAP) for developers looking to build innovative on-device Generative AI applications with Gemini Nano on Android.
Benefits of accessing AI foundation models with AICore
AICore enables the Android OS to provide and manage AI foundation models. This significantly reduces the cost of using these large models in your app, principally due to the following:
- Ease of deployment: AICore manages the distribution of Gemini Nano and handles future updates. You don't need to worry about downloading or updating large models over the network, nor impact on your app's disk and runtime memory budget.
- Access to hardware acceleration: AICore runtime is optimized to benefit from hardware acceleration. Your app gets the best performance on each device, and you don't need to worry about the underlying hardware interfaces.
Supported functionality
The following are the core capabilities that AICore supports at the moment:
- Supported Devices: AICore is currently available on Google Pixel 8 Pro and Samsung S24 Series devices.
- Supported Modalities: AICore currently supports text modality for Gemini Nano.
Device and modality support are areas of active investment.
Architecture
As a system-level module, you access AICore through a series of APIs in order to run inference on-device. You can also provide a LoRA fine-tuning block to further optimize the performance of Gemini Nano for your application. The following diagram outlines how an app accesses AICore to run Gemini Nano on-device.
Use cases
Some tasks you can accomplish with Gemini Nano through AICore are the following:
- AI-enhanced content consumption: For example, summarization, answering questions, and entity extraction.
- AI-enhanced content generation: For example, proofreading, grammar correction, writing assistance, and contextual smart replies.
Several Google products already use AICore on Pixel including Pixel Voice Recorder and Gboard.
Pixel voice recorder
The Pixel Voice Recorder application uses Gemini Nano and AICore to power an on-device summarization feature.
Gboard smart reply
Gboard leverages Gemini Nano with AICore to provide accurate smart reply capabilities on-device.