foundation-models-on-device

Generate and summarize text on-device with Apple's FoundationModels framework.

Updated Mar 15, 2026
One-click install
npx skills add https://github.com/abhishekdutta18/blogspro --skill foundation-models-on-device-abhishekdutta18
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: foundation-models-on-device
Source: https://github.com/abhishekdutta18/blogspro/tree/main/.claude/skills/foundation-models-on-device
Command: npx skills add https://github.com/abhishekdutta18/blogspro --skill foundation-models-on-device-abhishekdutta18

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a framework for integrating Apple's on-device language models into iOS applications, ensuring privacy and offline functionality.

Core Features & Use Cases

  • Text Generation & Summarization: Generate or summarize text directly on the device without cloud dependency.
  • Guided Generation: Use @Generable structures to produce structured outputs like profiles or data summaries.
  • Tool Calling: Invoke custom code or actions within the app, such as recipe searches or data extraction.
  • Streaming Responses: Support real-time UI updates with partial generation responses for improved user experience.
  • Use Case: Create a private note-taking app that generates summaries and extracts key points without sending data to external servers.

Quick Start

Use the foundation-models-on-device skill to implement offline, privacy-preserving text generation and structured data extraction in your app.

Frequently Asked Questions about foundation-models-on-device

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement on-device text generation in iOS for offline privacy?

On-device text generation in iOS uses Apple's FoundationModels framework to process natural language locally without cloud dependency. This ensures offline functionality and secure AI-powered features for privacy-sensitive applications.

What is the best way to generate structured data from an on-device language model in iOS?

Generating structured data from an on-device language model uses @Generable structures to guide output. This produces structured profiles or data summaries directly on the device without external servers.

Can I invoke custom code and functions during on-device language model processing?

Invoking custom code during on-device processing uses tool calling capabilities within the FoundationModels framework. This allows the language model to trigger app-specific actions like recipe searches or data extraction locally.

Does the FoundationModels framework support real-time streaming for UI updates?

The FoundationModels framework supports real-time streaming responses for on-device text generation. This provides partial generation outputs for immediate UI updates, improving user experience during local processing.

What iOS version is required for FoundationModels on-device language modeling?

FoundationModels on-device language modeling requires iOS 26 or later. This ensures compatibility with the framework's structured generation, tool invocation, and real-time streaming capabilities for privacy-preserving applications.