On-Device Function Calling in Google AI Edge Gallery
Summary
Google introduces FunctionGemma, a 270M parameter model for on-device function calling, enhancing mobile AI capabilities with instant interactions and offline functionality.
Why It Matters
This advancement allows developers to create responsive mobile applications that can perform tasks without internet connectivity, addressing the growing demand for efficient, offline AI solutions. It also highlights Google's commitment to optimizing AI models for mobile use, which is crucial for enhancing user experience in mobile applications.
Key Takeaways
- FunctionGemma enables on-device function calling with a compact model size.
- Google AI Edge Gallery now supports both Android and iOS, expanding accessibility for developers.
- The Mobile Actions and Tiny Garden demos showcase practical applications of on-device AI.
- Benchmarking features allow users to measure performance on their devices.
- Developers can fine-tune the model for custom applications, enhancing versatility.
On-Device Function Calling in Google AI Edge Gallery FEB. 26, 2026 Alice Zheng Product Manager Milen Ferev Software Engineer Wai Hon Law Software Engineer Share Facebook Twitter LinkedIn Mail The real magic of AI happens when a model stops merely describing the world and starts interacting with it. One such interaction mechanism is tool-use: the ability to predict and invoke function calls, for example to open apps or adjust system settings.Shifting tool-use on-device allows developers to build interactions that respond instantly while remaining fully functional regardless of connectivity. This enables, for instance, a natural language voice assistant to instantly create a calendar entry or navigate to a destination while you’re driving.However, bringing this level of capability to mobile remains a formidable task. Traditional function-calling has historically required large models with memory footprints far exceeding mobile hardware constraints. The real engineering challenge is to compress these models into a mobile footprint, while maintaining accuracy and without draining the battery.Today, we are excited to announce several major updates to Google’s on-device AI showcase app Google AI Edge Gallery:Building on the cross-platform capabilities of Google AI Edge, we are delighted to bring AI Edge Gallery to iOS in addition to Android, allowing developers to explore the same high-performance, on-device AI use cases powered by Gemma and other open-weight models directly wit...
![[2601.00809] A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}