skills.rest
FelixRauch
FelixRauchCOMMUNITY
Explore all skills by this author →
GitHub

apple-on-device-ai

Select Apple frameworks for on-device LLM and model deployment.

Updated May 10, 2026
Search Tags:#tool calling#structured output#foundation models#llama.cpp#on-device ai#core ml#mlx swift
One-click install
npx skills add https://github.com/FelixRauch/medat-figuren --skill apple-on-device-ai-felixrauch
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: apple-on-device-ai
Source: https://github.com/FelixRauch/medat-figuren/tree/main/.agents/skills/apple-on-device-ai
Command: npx skills add https://github.com/FelixRauch/medat-figuren --skill apple-on-device-ai-felixrauch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you select and deploy on-device AI options on Apple Silicon so you can build fast, private, reliable AI features without guessing the right framework or setup.

Core Features & Use Cases

  • Framework selection for on-device LLMs: Pick Foundation Models (iOS 26+/Apple Intelligence), Core ML for custom models, MLX Swift for high-throughput open-source inference, or llama.cpp for GGUF-based cross-platform inference.
  • Structured generation and tool calling: Use Foundation Models sessions with @Generable schemas for type-safe structured output and Tool protocol for autonomous tool execution.
  • Performance and optimization guidance: Apply Core ML model conversion, quantization/palettization/pruning, and backend routing patterns to meet latency and resource constraints.
  • Use-case fit and safety-first deployment: Handle availability checks, guardrails, session lifecycle, and fallbacks to avoid crashes on unsupported devices.

Quick Start

Use the apple-on-device-ai skill to design an on-device AI backend plan that matches your iOS version and model type, and includes an availability-checked fallback path.

Frequently Asked Questions about apple-on-device-ai

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

FAQPage Schema
How do I run on-device AI inference on Apple Silicon?▼

Select the correct backend for on-device AI: Foundation Models for iOS 26+, Core ML for custom models, MLX Swift for open-source LLMs, or llama.cpp for GGUF portability. This ensures fast, private inference across Apple frameworks.

How do I get structured output and tool calling with Apple Foundation Models?▼

Use Foundation Models sessions with typed @Generable schemas to generate type-safe structured output, and implement the Tool protocol to enable autonomous tool execution within your app.

What is the best way to convert and optimize custom models for Core ML?▼

The best way to optimize custom models for Core ML involves applying model conversion techniques alongside quantization, palettization, and pruning to meet specific latency and resource constraints on-device.

Can I use MLX Swift for high-throughput open-source LLM inference?▼

Yes, you can use MLX Swift for high-throughput open-source LLM inference on Apple Silicon, providing an optimized framework for running models directly on-device without external dependencies.

How do I handle availability checks and fallbacks for on-device AI?▼

Handle availability checks by implementing safety-first deployment patterns, including guardrails, session lifecycle management, and backend fallbacks to avoid crashes on unsupported Apple devices.

Does llama.cpp support GGUF model portability on Apple devices?▼

Yes, llama.cpp supports GGUF-based cross-platform inference on Apple devices, serving as a portable fallback option for running large language models when native frameworks are unavailable.

Related Skills

Explore More Software Engineering Skills→
onymchatonymchat

apple-on-device-ai

Guide framework selection and model optimization for on-device AI on Apple Silicon.

Official
Advanced
mintuzmintuz
21

local-ai-models

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

Community
Advanced
DFly7DFly7

apple-on-device-ai

Select, convert, and optimize on-device AI models for Apple platforms.

Community
Advanced
helix4uhelix4u

llama-cpp

Run LLM inference on CPU, Apple Silicon, and non-NVIDIA GPUs with GGUF models.

Community
Intermediate