This book teaches iOS and macOS developers how to take advantage of Apple Silicon powers with MLX Swift for machine learning on Apple devices. Build AI apps with custom models, quantization, vision-language, and speech synthesis.

What you get:

155 pages PDF
EPUB for Kindle
LLMs text to use with AI (~46,946 tokens)

MLX Swift for On-Device Intelligence

1. Introduction to MLX

Understanding the fundamentals of the MLX framework and its role in Apple development, including battery life considerations for on-device AI

2. Understanding AI Model Components

The components that make up AI models, including licensing considerations for App Store submissions

3. Loading Models with MLX Swift

How to load various model architectures using MLX Swift, with error handling for network failures and retry strategies

4. Getting Started with MLX Swift

Setting up your development environment and running your first MLX Swift code, with realistic performance expectations for different devices

5. Working with Pre-Trained Models

Using existing open-weights models for different tasks, including memory management and testing strategies for actual devices vs simulators

6. Model Quantization

Techniques to make large AI models smaller and faster for on-device performance, and when to avoid quantization

7. Text Embeddings with MLX Embedders

Using text embedding models to understand semantic meaning of text for search and comparison, with storage for large datasets

8. Customizing Generation Parameters

Fine-tuning parameters like temperature and top-k to control generative model output, with debugging techniques and parameter logging strategies

9. Vision-Language Models

Working with models that understand and describe image content, including image preprocessing best practices and quality considerations

10. MLX Swift Tools

Utilities for MLX Swift development, including integration tips for CI/CD pipelines and automated testing

11. Tool Use with Models

Enabling language models to interact with external tools and APIs, with security considerations and input validation strategies

12. Generative Vision with Image Tool

Working with models that generate and manipulate images based on text instructions, with result evaluation techniques and failure pattern analysis

13. Structured Generation with @Generable

Using Foundation Models' schema system to get type-safe, structured responses from MLX Swift models

14. On-Device TTS with MLX Audio

Building Kokoro and Sesame-based TTS with streaming and raw audio access for natural, human-like speech synthesis

Upcoming chapters:

15. Concurrent Session Processing & Performance Optimization

Advanced techniques for maximizing throughput with concurrent processing, batch optimization, KV cache management, and production-ready patterns for high-performance on-device AI applications

Use the code "STUDENT" for a discount if you are a student.

Exploring MLX Swift