Apple Foundation Models WWDC 2026: Multimodal + Python SDK

Apple shipped nine updates to the Foundation Models framework at WWDC 2026 on June 8 — and the one buried at the bottom of the release notes is the most interesting: the framework now runs on Linux. Alongside multimodal image input and a Python SDK, Apple also introduced a model abstraction layer that lets developers swap its on-device model for Anthropic Claude or Google Gemini without touching their downstream code.

LanguageModel protocol

Foundation Models has always been Apple’s model or nothing. That changes in iOS 27. A new LanguageModel protocol creates a shared interface that Apple’s on-device model, Google Gemini, and Anthropic Claude all implement. You write session logic once. You swap providers by changing one line.

The protocol has two key pieces:

• LanguageModel: Describes the model to the framework, declares capabilities, and provides configuration for the executor.
• LanguageModelExecutor: Handles prewarming resources and streaming generation back to the session.

Google’s Gemini models plug in through the Firebase Apple SDK. Anthropic has published a Swift package implementing the protocol for Claude. Core AI and MLX integrations enable local models on the Neural Engine and GPU.

Core AI framework

For developers who want to bring their own custom models into their app, Core AI is a brand-new framework designed to be the best way to run models on device. Core AI provides an architecture optimized for the unified memory and Neural Engine of Apple silicon, allowing developers to deploy full-scale LLMs locally.

Private Cloud Compute for Small Business

Developers enrolled in the App Store Small Business Program with fewer than 2 million total first-time App Store downloads can access the next generation of Apple Foundation Models running on Private Cloud Compute at no cloud API cost.

Linux and open source

Apple open-sourced the Foundation Models framework utilities package and confirmed that the core framework runs on Linux servers via Swift’s open-source runtime. This is primarily aimed at data scientists and ML researchers who want to use Apple’s on-device model in Python tooling or server-side scripting contexts.