An AI-driven journey in porting Qwen 3VL 4B vision model from MLX Python to Swift, featuring coding sessions with GPT-5 Codex, debugging with Sonnet 4.5, and performance optimizations with Haiku 4.5 to achieve code parity.
Discover llm-tool, a CLI utility for testing MLX Swift models on macOS. Learn how to use with Xcode or Cursor, easily evaluate LLMs and VLMs with generation parameters. Perfect for Swift developers wanting to experiment with AI capabilities before integrating MLX models into apps.
Learn to implement tool use and function calling in MLX Swift for iOS/macOS apps. Enable LLMs to access real-time data, interact with WeatherKit, and handle external systems. Comprehensive guide with code examples for Swift developers implementing AI capabilities.
An iOS developer explores Replit's new AI agent that promises to turn ideas into apps without coding. While testing an IF app concept, they encounter functionality issues. Despite being optimistic about AI's future in app development, they conclude the tool isn't yet ready for general users.
Learn how to convert Hugging Face models to MLX format for optimized performance on Apple devices. This step-by-step guide covers setting up Python, installing MLX-LM, logging into Hugging Face, & converting models with quantization for iOS apps. Perfect for developers new to Python and MLX!