Core AI is Apple's new Python-based suite for converting, optimizing, and deploying PyTorch models on Apple Silicon. It covers the full lifecycle from torch.export through compression via coreai-opt to on-device inference, with a companion Core AI Debugger app for runtime inspection.
• Convert any PyTorch model to an optimized .aimodel asset with a handful of Python calls — no manual Metal or ANE tuning required
• Config-driven quantization presets (w4, int8, FP8) shrink large models like SAM3 from 3 GB to ~430 MB while keeping the same export pipeline
• Core AI Debugger lets you visualize graph structure, inspect intermediate tensors per-operation, and validate against a PyTorch reference run — all without code changes
Foundation Models is a new Apple framework introduced in iOS 27 that gives developers on-device access to the same Apple Intelligence language model powering system features, enabling text generation, structured output, and tool-calling entirely on-device without a network connection.
Visual Intelligence brings iOS 17's Visual Look Up capabilities to a new developer-facing API surface in iOS 27, letting apps pipe live camera frames or static images through on-device scene understanding to extract subjects, text, barcodes, and rich semantic labels without any cloud round-trip.
iOS 27 opens the Foundation Models framework to third-party LLM providers via a new public LanguageModel protocol, enabling anyone to integrate custom, server-based, or open-source models using the same Swift API as Apple's on-device system model.
In-depth guide
iOS 27 On-Device AI & Apple Intelligence →App Schemas let developers describe their app's content and actions using pre-defined domain schemas (like the Calendar domain) so Siri can understand, search, and act on app data without custom NLP. Entities conforming to IndexedEntity are donated to Spotlight's semantic index, enabling natural-language queries over app content.