Apple On Device Ai

This is the comprehensive guide you need if you're shipping on-device AI on Apple platforms. It walks you through Foundation Models for zero-setup text generation and structured output with @Generable, Core ML for converting and optimizing custom models with quantization and Neural Engine deployment, MLX Swift for maximum throughput with open-source LLMs on Apple Silicon, and llama.cpp for cross-platform GGUF inference. The framework selection router at the top is genuinely helpful for cutting through the decision paralysis. Heavy on code examples for tool calling, streaming, session management, and availability checking. If you're building anything that runs AI locally on iPhone or Mac, this covers the entire stack.

skills.sh installs: 4.2K
GitHub stars: 1.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add dpearson2699/swift-ios-skills --skill apple-on-device-ai --agent claude-code

Installs into .claude/skills of the current project.

Files

On-Device AI for Apple Platforms

Guide for selecting, deploying, and optimizing on-device ML models. Covers Apple Foundation Models, Core ML, MLX Swift, and llama.cpp.

Framework Selection Router
Apple Foundation Models Overview
Core ML Overview
MLX Swift Overview
Multi-Backend Architecture
Performance Best Practices
Common Mistakes
Review Checklist
References

Framework Selection Router

Use this decision tree to pick the right framework for your use case.

Apple Foundation Models

When to use: Text generation, summarization, entity extraction, structured output, and short dialog on iOS 26+ / macOS 26+ devices with Apple Intelligence enabled. No app-managed API key, network round trip, or model hosting; still handle system model asset readiness.

SKILL.md on GitHub