WWDC26: Integrate on-device AI models into your app using Core AI | Apple

Discover a curated collection of popular open-source models — including Qwen, Mistral, SAM3, and more — optimized for Apple silicon using the new Core AI Framework. Learn how to download, run, and benchmark models on your Mac, and integrate them into your app with just a few lines of code. Explore a new workflow for model compilation and on-device specialization to speed up first-time model load. Find out how to profile and optimize runtime performance with Core AI tools in Xcode. Explore related documentation, sample code, and more: Core AI PyTorch Extensions: https://apple.github.io/coreai-torch Core AI Python: https://apple.github.io/coreai-torch/... Core AI Optimization: https://apple.github.io/coreai-optimi... Core AI: https://developer.apple.com/documenta... Compiling Core AI models ahead of time: https://developer.apple.com/documenta... Explore distributed inference and training with MLX: https://developer.apple.com/videos/pl... Run local agentic AI on the Mac using MLX: https://developer.apple.com/videos/pl... Explore numerical computing in Swift with MLX: https://developer.apple.com/videos/pl... Build local AI agents on Mac with MLX: https://developer.apple.com/videos/pl... 00:00 - Introduction 01:16 - App concept: camera-based vocab learning 02:52 - Model discovery 07:40 - Getting models with the Core AI models repository 08:37 - Integration 10:55 - Writing the Swift integration code 13:05 - Diagnosing model specialization latency 14:40 - Deployment 17:00 - Ahead-of-time (AOT) compilation 18:03 - iOS demo 19:57 - Multiplatform 23:06 - Next steps More Apple Developer resources: Video sessions: https://apple.co/VideoSessions Documentation: https://apple.co/DeveloperDocs Forums: https://apple.co/DeveloperForums App: https://apple.co/DeveloperApp