Blaizzy/mlx-vlm

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Python5.4K stars740 forks+416 today

Topics

#llava#llm#mlx#vision-transformer#apple-silicon#idefics#local-ai#paligemma#vision-framework#vision-language-model#florence2#molmo#pixtral

What it does

MLX-VLM is a Python package for running inference and fine-tuning of Vision-Language Models on Mac, enabling users to interact with models through CLI, Gradio UI, or scripts. It supports various models including those that handle OCR and multimodal tasks.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-04-25

Creator kit

Hook

Discover MLX-VLM: The ultimate toolkit for running Vision-Language Models on your Mac! 🚀 #MachineLearning #MacOS

Content angles

Create tutorials showcasing how to use MLX-VLM with different models.
Develop a comparison blog post between MLX-VLM and other similar tools.
Publish a step-by-step guide on fine-tuning custom Vision-Language Models using MLX-VLM.

Who should care

AI researchers, data scientists, developers interested in machine learning on macOS.