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
related skills
semantically similar in the cross-vendor index
don't have the plugin yet? install it then click "run inline in claude" again.
+covers multiple inference backends with concrete selection criteria rather than prescribing one path
+explicitly lists 10 common mistakes and memory constraints (60% ram limit), showing awareness of real deployment failure modes
~trigger phrases are absent - no examples like 'generate text offline on ios 18' or 'run vision model without server'; reads as reference docs not executable skill
~procedure lacks numbered steps and concrete ios/macos code; 'choose foundation models for zero-setup' is a statement, not a runnable procedure with inputs/outputs per step
~edge case coverage minimal - acknowledges context window budgeting and availability checks but no recovery paths or handling examples (what if quantization fails, what if model memory exceeds device, how to degrade gracefully)
