The DropJune 20, 2026via InfoQ AI/ML
Apple Launches Core AI for Apple-Silicon Optimized On-Device Generative AI
Why it matters
Apple's Core AI framework democratizes on-device generative AI for millions of developers, shifting the AI inference battleground from cloud to silicon—with major implications for privacy, latency, and the economics of model deployment.
Key signals
- Core AI announced at WWDC 26 as official successor to Core ML
- Supports custom-converted PyTorch models and pre-optimized open-source models
- Designed for Apple-silicon optimization
- Enables on-device LLM and generative AI inference
- Eliminates cloud dependency for inference workloads
The hook
Apple just gave every developer a framework to run LLMs on-device. No cloud. No latency. No data leaving the phone.
At WWDC 26, Apple announced the Core AI framework, the official successor to Core ML. It is designed to allow developers to run large language models and generative AI entirely on-device, supporting both custom-converted PyTorch models and pre-optimized open-source models.
By Sergio De Simone