what is there in CoreAI
Asked on 2026-08-13
1 search
Core AI is Apple’s new on-device AI framework for running models directly on Apple platforms, with the goal of being the best way to bring and run models in your apps.
What it includes:
- A modern Swift API for loading and running models safely and efficiently
- High-performance inference across the CPU, GPU, and Neural Engine
- Python/PyTorch-based tools to convert and optimize models for Core AI
- Deep customization options like:
- fine-grained inference management
- model specialization
- custom GPU kernels
- A new developer toolchain with:
- ahead-of-time compilation
- Core AI Instruments
- a visual debugger that traces tensor values back to Python source
It’s also designed to scale from smaller on-device models to large ones, all running locally with:
- no server required
- no cost per token
- low latency
Relevant sessions:
- Meet Core AI
- Dive into Core AI model authoring and optimization
- Integrate on-device AI models into your app using Core AI

Platforms State of the Union
Discover the newest advancements on Apple platforms.

Meet Core AI
Discover Core AI, Apple’s new framework for on-device AI model deployment. Tour the ecosystem, from Python libraries for converting, authoring, and optimizing models, to a Swift API for simple plug-and-play inference and advanced use cases with strict latency and memory requirements. Explore the new Core AI models repository with ready-to-run examples for popular architectures. See how deep Xcode integration, including ahead-of-time model compilation, streamlines the workflow so you can deliver smarter, more responsive app experiences.

Dive into Core AI model authoring and optimization
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.
