Uploaded June 2026 | Updated September 2026, 1 week ago

---

Dive into the complete custom model deployment workflow for Apple silicon with the new Core AI framework. Discover powerful techniques for authoring models using custom Metal kernels, alongside platform-aware compression strategies. The new Core AI Debugger offers deep intrinsic analysis, and AI-assisted workflows guide you from initial concept to optimized on-device execution.

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
Inspecting, debugging, and profiling Core AI models: developer.apple.com/documentation/CoreAI/inspecting-debugging-and-profiling-core-ai-models
Inspecting Core AI models with Core AI Debugger: developer.apple.com/documentation/CoreAI/inspecting-core-ai-models-with-core-ai-debugger
Core AI: developer.apple.com/documentation/CoreAI
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
01:49 - Models and skills
03:27 - Python workflow
05:54 - Model optimization
10:40 - Core AI Debugger
19:27 - Advanced authoring
20:43 - Custom Metal kernels
23:01 - Model re-authoring
28:46 - Next steps

More Apple Developer resources:
Video sessions: apple.co/VideoSessions
Documentation: apple.co/DeveloperDocs
Forums: apple.co/DeveloperForums
App: apple.co/DeveloperApp