All Articles

Learn how to integrate MLX Swift's vision capabilities into your iOS apps for on-device AI inference implementing Vision Language Models (VLMs) using Qwen3-VL-4B-Instruct, enabling features like image description, visual Q&A, object detection, and video understanding running locally on Apple silicon devices.

Learn how to integrate custom large language models into iOS/macOS apps using MLX Swift. This guide shows how to configure and run models like Qwen 2.5 locally on Apple silicon, with tips for handling memory limits and entitlements for on-device AI inference.

Learn how to convert and configure the Hermes 3 language model for iOS apps using MLX Swift. This guide walks through converting Hugging Face models to MLX format, setting up model configurations, and implementing on-device inference.

Explore the power of GenerateParameters in MLX Swift for text generation. Learn how to customize temperature, top-p sampling, and repetition penalties to control model outputs. From creative writing to technical documentation, discover practical examples for optimizing language model parameters.