What's new with Core AI?
Asked on 2026-08-20
1 search
Core AI is Apple’s new on-device AI framework and toolchain for building and running models across Apple platforms, and the 2026 WWDC sessions show several big additions:
- It’s broader than a framework now: Core AI covers the whole model lifecycle, including model authoring, conversion, optimization, debugging, integration, and deployment.
- Modern Swift API: It offers a memory-safe Swift API designed for high performance.
- Apple Silicon acceleration: Core AI runs across the CPU, GPU, and Neural Engine and is optimized for Apple Silicon.
- Python/PyTorch workflow support: You can use familiar Python and PyTorch-based tools to prepare models, convert them, and optimize them for Core AI.
- Customization: It supports advanced tuning like fine-grained inference management, model specialization, and custom Metal/GPU kernels.
- New developer tools: Apple highlighted a new toolchain with ahead-of-time compilation, Core AI Instruments, and a visual debugger that traces tensor values back to Python source.
- Local-only execution: Models run on-device, so there’s no server dependency, no token cost, and lower latency.
- Scales from small to large models: Apple showed use cases from small vision models to multi-billion-parameter LLMs.
- Available on Apple Silicon: Core AI is available on all Apple Silicon to help build private, local intelligence features.
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
If you want, I can also summarize what’s new in model conversion, app integration, or debugging/profiling specifically.
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.
Platforms State of the Union
Discover the newest advancements on Apple platforms.
Integrate on-device AI models into your app using Core AI
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.