iOS On-Device AI Models
Production-ready guide for implementing on-device AI models in iOS apps using Apple's Foundation Models framework and MLX Swift.
When to Use This Skill
- •Implementing local LLM inference in iOS apps
- •Building chat interfaces with Foundation Models
- •Integrating Vision Language Models (VLMs)
- •Adding text embeddings or image generation
- •Implementing tool/function calling with LLMs
- •Managing multi-turn conversations
- •Optimizing memory usage for on-device models
- •Supporting internationalization in AI features
Core Principles
- •Availability First - Always check model availability before initialization
- •Stream Responses - Provide progressive UI updates for better UX
- •Session Persistence - Reuse LanguageModelSession for multi-turn conversations (Foundation Models)
- •Memory Awareness - Use quantized models and monitor memory usage
- •Async Everything - Load models asynchronously, never block the main thread
- •Locale Support - Use supportsLocale(_:) and locale instructions for Foundation Models
Quick Reference
Framework Comparison
| Topic | Guide |
|---|---|
| Framework comparison and selection | framework-selection.md |
Foundation Models (Apple's Framework)
| Topic | Guide |
|---|---|
| Setup and configuration | foundation-models/setup.md |
| Chat patterns and conversations | foundation-models/chat-patterns.md |
MLX Swift (Advanced Features)
| Topic | Guide |
|---|---|
| Setup and configuration | mlx-swift/setup.md |
| Chat patterns with custom models | mlx-swift/chat-patterns.md |
| Vision Language Models (VLMs) | mlx-swift/vision-patterns.md |
| Tool calling, embeddings, structured gen | mlx-swift/advanced-patterns.md |
| Model quantization with MLX-LM | mlx-swift/quantization.md |
Shared (Both Frameworks)
| Topic | Guide |
|---|---|
| Best practices and optimization | shared/best-practices.md |
| Error handling and recovery | shared/error-handling.md |
| Testing strategies | shared/testing.md |
Quick Decision Trees
Which framework should I use?
code
Do you need advanced features like:
- Vision Language Models (VLMs)
- Image generation
- Custom models beyond the system model
├── Yes → MLX Swift (references/mlx-swift/)
└── No → Is this a standard chat interface?
├── Yes → Foundation Models (simpler, recommended)
└── No → Check framework-selection.md for guidance
Where should I start?
code
New to on-device AI?
└── Start with Foundation Models:
1. Read framework-selection.md
2. Follow foundation-models/setup.md
3. Implement foundation-models/chat-patterns.md
Need advanced features?
└── Use MLX Swift:
1. Read framework-selection.md
2. Follow mlx-swift/setup.md
3. Choose pattern:
- Chat: mlx-swift/chat-patterns.md
- Vision: mlx-swift/vision-patterns.md
- Advanced: mlx-swift/advanced-patterns.md
Where should my model loading code live?
code
Is this model shared across features?
├── Yes → Create @Observable service in app/services/
└── No → Is it feature-specific?
├── Yes → Create @Observable class in feature/
└── No → Load inline with @State (simple cases only)
How should I handle conversations?
code
Foundation Models:
└── Reuse LanguageModelSession for context
(references/foundation-models/chat-patterns.md #multi-turn)
MLX Swift:
└── Implement custom context management
(references/mlx-swift/chat-patterns.md)
What generation parameters should I use?
code
What's the use case? Factual answers (summaries, facts) └── temperature: 0.1-0.3 Balanced (chat, Q&A) └── temperature: 0.6-0.8 Creative (storytelling, ideas) └── temperature: 0.9-1.2 See references/shared/best-practices.md for details