The Google AI Edge Gallery app is now available for Android users. It can be downloaded from the official Google AI Edge repository on GitHub. A version for iOS is expected soon. The program is aimed at developers, researchers, and enthusiasts who want to experiment with generative AI models directly on their devices without the need for an internet connection.
AI Edge Gallery supports a number of open models, including “Gemma 3”, “Gemma 3n”, and “Qwen 2.5”. Users can interact with AI, process images, perform tasks in the “Prompt Lab”, and connect their own models in LiteRT format for testing. The app ensures local processing of all data, which helps maintain privacy and information security.
Among the main features of the app are question and answer based on images, text summarization, code generation, multi-step dialogues, and real-time performance metrics display. For optimal performance, it is recommended to use devices with Android version ten or higher, at least six gigabytes of RAM, and a modern processor.
The project is open-source and distributed under the Apache 2.0 license, allowing it to be freely used in various fields. Google invites the community to participate in testing and leave feedback, and promises to add voice function support, optimization for iOS, and improved hardware acceleration in future updates.
