Resources

Core AI

Core AI is a set of new technologies for on device AI, to help you in your journey for bringing AI models from PyTorch to production, especially for deploying full-scale LLMs and other powerful generative models locally on Apple Silicon.

• Get started with Core AI
• Core AI framework
• Core AI models on GitHub
• Core AI PyTorch extensions on GitHub
• Core AI Optimization on GitHub
• Core AI Debugger

Foundation Models framework

The Foundation Models framework is a native Swift API that gives you direct access to the same on-device model that powers Apple Intelligence. You can now work with any language model, including Apple Foundation Models, or any other provider that conforms to the Language Model protocol.

• Foundation Models framework
• Human Interface Guidelines for Generative AI

Core ML

Integrate machine learning models into your app with Core ML frameworks. Your app uses Core ML APIs and user data to make predictions, and to train or fine-tune models, all on a person’s device.

• Core ML framework
• Core ML models

Core ML converters

Convert models from TensorFlow, PyTorch, and other libraries to Core ML.

• Core ML tools

Machine learning APIs

Bring intelligent on-device machine learning powered features, object detection in images and video, language analysis, and sound classification, to your app with just a few lines of code.

• Vision
• Natural Language
• Speech
• Sound
• Translation