Uploaded June 2026 | Updated September 2026, 1 week ago
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: apple.github.io/coreai-torch
Core AI Python: apple.github.io/coreai-torch/main/coreai-core
Core AI Optimization: apple.github.io/coreai-optimization
Core AI: developer.apple.com/documentation/CoreAI
Compiling Core AI models ahead of time: developer.apple.com/documentation/CoreAI/compiling-core-ai-models-ahead-of-time
Explore distributed inference and training with MLX: developer.apple.com/videos/play/wwdc2026/233
Run local agentic AI on the Mac using MLX: developer.apple.com/videos/play/wwdc2026/232
Explore numerical computing in Swift with MLX: developer.apple.com/videos/play/wwdc2026/328
Build local AI agents on Mac with MLX: developer.apple.com/videos/play/wwdc2026-shorts/229
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: apple.co/VideoSessions
Documentation: apple.co/DeveloperDocs
Forums: apple.co/DeveloperForums
App: apple.co/DeveloperApp
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: apple.github.io/coreai-torch
Core AI Python: apple.github.io/coreai-torch/main/coreai-core
Core AI Optimization: apple.github.io/coreai-optimization
Core AI: developer.apple.com/documentation/CoreAI
Compiling Core AI models ahead of time: developer.apple.com/documentation/CoreAI/compiling-core-ai-models-ahead-of-time
Explore distributed inference and training with MLX: developer.apple.com/videos/play/wwdc2026/233
Run local agentic AI on the Mac using MLX: developer.apple.com/videos/play/wwdc2026/232
Explore numerical computing in Swift with MLX: developer.apple.com/videos/play/wwdc2026/328
Build local AI agents on Mac with MLX: developer.apple.com/videos/play/wwdc2026-shorts/229
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: apple.co/VideoSessions
Documentation: apple.co/DeveloperDocs
Forums: apple.co/DeveloperForums
App: apple.co/DeveloperApp
