skills.rest
unju-ai
unju-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

foundation-models-on-device

Integrate Apple's FoundationModels framework for on-device LLM text generation in iOS 26+.

Updated Mar 2, 2026
Search Tags:#tool calling#swift#ios#generable#foundationmodels#on-device llm
One-click install
npx skills add https://github.com/unju-ai/ecc --skill foundation-models-on-device-unju-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: foundation-models-on-device
Source: https://github.com/unju-ai/ecc/tree/main/skills/foundation-models-on-device
Command: npx skills add https://github.com/unju-ai/ecc --skill foundation-models-on-device-unju-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables developers to integrate powerful on-device Large Language Models (LLMs) into their iOS applications, ensuring privacy and offline functionality.

Core Features & Use Cases

  • On-Device Text Generation: Generate text, summaries, and creative content directly on the user's device.
  • Structured Data Generation: Use the @Generable macro to output data directly into Swift types.
  • Tool Calling: Allow the LLM to invoke custom code for specific tasks.
  • Snapshot Streaming: Stream partially generated structured responses for real-time UI updates.
  • Use Case: Build a private journaling app that summarizes user entries on-device, or a note-taking app that automatically extracts action items into a structured format without sending data to the cloud.

Quick Start

Check if the FoundationModels are available on the device before attempting to create a language model session.

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 use on-device LLM text generation in an iOS app?▼

Structured output from an on-device LLM is achieved using the `@Generable` macro in Swift. This feature maps the generated text directly into specific Swift types, allowing you to extract data like action items into a structured format.

Can I implement tool calling with FoundationModels on iOS?▼

Tool calling with FoundationModels on iOS is fully supported. You can allow the on-device LLM to invoke custom Swift code for specific tasks, extending the model's capabilities within your application's offline environment.

Does on-device LLM support in iOS require a specific Xcode or Swift version?▼

On-device LLM support in iOS requires Swift and a standard Xcode development environment. You must also ensure the application targets iOS 26 or later, and verify that FoundationModels are available on the user's specific device before creating a session.

What is the best way to stream partially generated LLM responses in Swift?▼

The best way to stream partially generated LLM responses in Swift is using snapshot streaming. This feature streams structured responses from the FoundationModels framework in real-time, enabling immediate UI updates as the data is generated.

Why should I use an on-device LLM instead of a cloud-based API for my iOS app?▼

An on-device LLM ensures complete user privacy and full offline functionality by processing all text generation locally. This approach is ideal for private journaling or note-taking apps where sending user data to the cloud is undesirable.

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
ROLLED740ROLLED740
1

foundation-models-on-device

Integrate Apple's FoundationModels into iOS apps for on-device text generation.

Community
Advanced
yebotyebot
9

swift

Build native Apple platform apps with Swift and SwiftUI.

Community
Intermediate
mintuzmintuz
21

local-ai-models

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

Community
Advanced