apple-on-device-ai

SKILL.md

Deploy on-device AI across Apple platforms using Foundation Models, Core ML, MLX Swift, and llama.cpp.

Choose Foundation Models for zero-setup text generation and structured output on iOS 26+; Core ML for custom vision and NLP models; MLX Swift for maximum throughput on Apple Silicon; llama.cpp for cross-platform GGUF inference

Foundation Models includes session management, @Generable macros for type-safe structured output, tool calling, and streaming with always-enforced guardrails

Core ML supports PyTorch, TensorFlow, and scikit-learn conversion via coremltools, with quantization, palettization, and pruning for Neural Engine optimization

Multi-backend architecture patterns, memory management rules (60% RAM limit on iOS), and 10 common mistakes to avoid including availability checks, context window budgeting, and concurrent request handling

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.

Contents

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