Google Launches AI Edge Gallery App to Run Hugging Face Models Offline on Mobile

Last week, Google quietly unveiled a new app, Google AI Edge Gallery, which allows users to run various AI models from the Hugging Face platform directly on their phones.

Last week, Google quietly unveiled a new app, Google AI Edge Gallery, which allows users to run various AI models from the Hugging Face platform directly on their phones. Available for Android and coming soon to iOS, the app allows users to download and run models offline, taking advantage of their phone’s local processing power. This is a significant shift from traditional cloud-based AI models, which, while more powerful, require internet access and can raise concerns about data privacy and connectivity.

The app is designed to cater to users who prefer running models offline, giving them more control over their data and eliminating the need for a stable internet connection. The app offers a range of features, including the ability to generate images, answer questions, and write or edit code, all powered by the Hugging Face models. On the app’s home screen, users can easily access task shortcuts like “Ask Image” or “AI Chat,” which then lead them to models suitable for those tasks, such as Google’s own Gemma 3n model.

Image Credits: Google

In addition to its core capabilities, Google AI Edge Gallery also introduces a “Prompt Lab” feature, which allows users to perform single-turn tasks such as summarising text or rewriting it. The lab includes several templates and settings for users to customise their tasks, making the experience more flexible and user-friendly. However, performance can vary depending on the phone’s hardware and the model size. Larger models may take longer to complete tasks compared to smaller, more lightweight ones.

Despite some variation in performance across different devices, Google positions the AI Edge Gallery as a useful tool for developers and everyday users alike. The app is in its “experimental Alpha release,” and Google is inviting the developer community to provide feedback on the app’s functionality. Google has made the app available under an Apache 2.0 license, meaning it can be used freely in both commercial and non-commercial contexts.

This development marks another step in Google’s effort to democratise AI, making advanced models more accessible and easier to use for people on the go, regardless of their internet connectivity. As more people embrace AI in their daily lives, this app could become a key tool for those seeking to explore AI’s potential without relying on cloud-based services.

💡 Found this helpful? Click below to share it with your network and spread the value:
Havilah Mbah
Havilah Mbah

Havilah is a staff writer at The Algorithm Daily, where she covers the latest developments in AI news, trends, and analysis. Outside of writing, Havilah enjoys cooking and experimenting with new recipes.

Leave a Reply

Your email address will not be published. Required fields are marked *