Deploy models on-device with Core AI
Apple's Core AI lets developers run cutting-edge AI models on-device for private, offline, zero-cost inference.
“Inference happens on device so data stays private, AI features can be readily available and work offline, and there is no per inference cost to you or your users.”
Apple introduced Core AI at WWDC, a framework enabling developers to deploy AI models on-device across iPhone, iPad, and Mac with private, offline inference and no per-inference cost. It matters because it signals Apple's push to make on-device AI the default foundation for app intelligence, contrasting with cloud-based AI economics.