skills.rest
mazicimert
mazicimertCOMMUNITY
Explore all skills by this author →
GitHub

foundation-models

Configure Apple Foundation Models for on-device text generation in Swift apps.

Updated Mar 1, 2026
Search Tags:#llm#swift#ios#foundation-models#privacy#on-device#tool-calling
One-click install
npx skills add https://github.com/mazicimert/RunDom --skill foundation-models-mazicimert
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: foundation-models
Source: https://github.com/mazicimert/RunDom/tree/main/.claude/skills/apple-intelligence/foundation-models
Command: npx skills add https://github.com/mazicimert/RunDom --skill foundation-models-mazicimert

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

On-device LLM integration with Apple's Foundation Models enables privacy-preserving AI features by running models locally in app.

Core Features & Use Cases

  • On-device text generation, structured output, and tool calling without sending data to external servers.
  • Easy integration with Swift using FoundationModels.
  • Use case: build privacy-focused AI assistants, content summarization, and command execution within the app.

Quick Start

Configure and run Apple's Foundation Models on-device to enable privacy-preserving AI features in your app.

Frequently Asked Questions about foundation-models

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

FAQPage Schema
How do I run an LLM on-device in iOS for privacy-preserving text generation?▼

To run an LLM on-device in iOS, use the FoundationModels framework in Swift to configure models, create sessions, and manage local inference without sending data to external servers.

Can I use Apple's Foundation Models to execute tool calling within my iOS app?▼

Yes, Apple's Foundation Models support on-device tool calling within iOS apps, enabling command execution and AI assistant interactions locally using Swift-based code.

What is the best way to generate structured output with on-device LLMs in Swift?▼

The best way to generate structured output with on-device LLMs is by integrating the FoundationModels framework, which allows Swift apps to produce structured data directly during local inference.

Do I need an internet connection to use FoundationModels for on-device inference?▼

No, FoundationModels runs inference locally on the device, meaning no internet connection is required to generate text, produce structured output, or execute tool calls.

How does on-device LLM integration compare to cloud-based APIs for iOS apps?▼

On-device LLM integration differs from cloud-based APIs by running models locally within the app, ensuring user data never leaves the device for maximum privacy.

What are the limitations of using FoundationModels for on-device AI in iOS?▼

Limitations of FoundationModels include requiring Swift-based code and integration with the FoundationModels framework, restricting use to iOS applications that can run local inference.

Related Skills

Explore More Software Engineering Skills→
GGEduGGEdu

foundation-models-on-device

Enable on-device text generation with FoundationModels for iOS 26+ apps.

Community
Advanced
Michae2xlMichae2xl

foundation-models-on-device

Generate text, structured output, and tool calls on iOS 26 with FoundationModels.

Community
Advanced
mintuzmintuz
21

local-ai-models

Integrate on-device AI models in iOS apps using Foundation Models and MLX Swift.

Community
Advanced
KanakMalpaniKanakMalpani

foundation-models-on-device

Integrate Apple FoundationModels on-device for private LLM tasks in iOS apps.

Community
Advanced