Google’s Latest Tool Makes Offline AI Accessible to Everyone

Last week, Google launched the Google AI Edge Gallery app, allowing users to download and execute AI models from Hugging Face directly on their phones. Currently available on Android, with an iOS version on the way, the app supports offline AI tasks. Marketed as an “experimental Alpha release,” it can be downloaded from GitHub along with installation instructions. Users can take advantage of features like “Ask Image” and “AI Chat,” with a selection of compatible models, including Google’s Gemma 3n. The app enables users to perform tasks like image generation, question answering, and code writing/editing using their device’s processing power. It also includes a “Prompt Lab” for tasks such as text summarization and rewriting. Google warns that performance may vary based on device hardware, with larger models requiring more processing time. The company is seeking feedback from developers, and the app is available under an Apache 2.0 license for broad usage.

Source link