skills.rest
cescrafli
cescrafliCOMMUNITY
Explore all skills by this author →
GitHub

foundation-models-on-device

Generate on-device LLM responses with FoundationModels for iOS 26+ apps.

Updated Mar 26, 2026
Search Tags:#ai#streaming#privacy#generable#on-device#tool-calling#foundationmodels
One-click install
npx skills add https://github.com/cescrafli/compyrasion --skill foundation-models-on-device-cescrafli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: foundation-models-on-device
Source: https://github.com/cescrafli/compyrasion/tree/main/skills/foundation-models-on-device
Command: npx skills add https://github.com/cescrafli/compyrasion --skill foundation-models-on-device-cescrafli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

On-device LLM generation enables private, offline AI responses without cloud data transmission.

Core Features & Use Cases

  • On-device execution for privacy: All processing happens on the device, with no data sent to external servers.
  • Structured outputs with @Generable: Generate typed, structured results instead of free text.
  • Tool calling and streaming: Integrate domain tools and stream results to UI for real-time updates.
  • Use cases include building privacy-first chat assistants, data extraction workflows, and offline AI features in iOS apps.

Quick Start

Initialize an on-device FoundationModels session and generate a concise, privacy-preserving response to a user prompt.

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 generate structured outputs from an on-device LLM in iOS?▼

On-device LLM generation enables private, offline AI responses without cloud data transmission. It uses FoundationModels to process text generation, structured outputs, and tool calling directly on iOS devices.

Can I stream LLM responses directly to my iOS app UI?▼

Yes, you can stream LLM responses to your iOS app UI using snapshot streaming patterns. This FoundationModels feature provides real-time updates during on-device generation without cloud transmission.

Does on-device LLM generation support tool calling for iOS apps?▼

Yes, on-device LLM generation supports tool calling within FoundationModels sessions. You can integrate domain tools alongside @Generable structured outputs and snapshot streaming for offline iOS apps.

What are the limitations of using FoundationModels for offline AI?▼

Limitations of using FoundationModels for offline AI include requiring careful model availability checks and single-session requests. It also requires iOS 26+ and proper Generable types to ensure reliability.

How do I ensure privacy during on-device text generation?▼

To ensure privacy during on-device text generation, use FoundationModels sessions which process all data locally. No user data is sent to external servers, keeping offline AI responses completely private.

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
KanakMalpaniKanakMalpani

foundation-models-on-device

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

Community
Advanced
mintuzmintuz
21

local-ai-models

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

Community
Advanced
agentmattersagentmatters
3

foundation-models-on-device

Integrate Apple FoundationModels for on-device text generation and tool calling in Swift iOS apps.

Official
Advanced