fundament models
Asked on 06/16/2025
2 searches
The Foundation Models framework was introduced at WWDC 2025, providing access to an on-device large language model through a Swift API. This framework is available on macOS, iOS, iPadOS, and VisionOS, and it allows developers to enhance app features with capabilities like personalized search suggestions, content generation, text summarization, and more, all while maintaining user privacy since it runs on-device.
Key features of the Foundation Models framework include:
-
Guided Generation: This feature allows developers to generate structured output, such as JSON or CSV, using the
Generable
macro. This helps in creating reliable structured data from the model's output. -
Snapshot Streaming: Instead of streaming raw deltas, the framework uses snapshots to represent partially generated responses, which are more robust for structured output.
-
Tool Calling: The model can autonomously call custom functions defined in your app, allowing it to perform tasks like fetching up-to-date content or taking specific actions.
-
Stateful Sessions: This feature supports multi-turn interactions, maintaining context across multiple exchanges with the model.
-
AI Safety and Prompt Design: The framework includes built-in guardrails to ensure safe app experiences and provides best practices for prompt design to avoid misuse or potential harm.
For more detailed information, you can explore sessions like Meet the Foundation Models framework and Deep dive into the Foundation Models framework.

Meet the Foundation Models framework
Learn how to tap into the on-device large language model behind Apple Intelligence! This high-level overview covers everything from guided generation for generating Swift data structures and streaming for responsive experiences, to tool calling for integrating data sources and sessions for context management. This session has no prerequisites.

Discover machine learning & AI frameworks on Apple platforms
Tour the latest updates to machine learning and AI frameworks available on Apple platforms. Whether you are an app developer ready to tap into Apple Intelligence, an ML engineer optimizing models for on-device deployment, or an AI enthusiast exploring the frontier of what is possible, we’ll offer guidance to help select the right tools for your needs.

Explore prompt design & safety for on-device foundation models
Design generative AI experiences that leverage the strengths of the Foundation Models framework. We’ll start by showing how to design prompts for the on-device large language model at the core of Apple Intelligence. Then, we’ll introduce key ideas around AI safety, and offer concrete strategies to make your generative AI features safe, reliable, and delightful.