• Picks
  • Discover
  • Alternatives
  • About

© 2026 Willet

  • Newsletter
  • About
  • FAQ
  • Terms
  • Privacy & Cookies
Join the Discord (opens in a new tab)
Prince Canuma avatar

MLX-VLM

Run and fine-tune vision language models locally on Apple silicon

  • AI models and runtimes
View on GitHub

What it is

A Python package built on Apple's MLX for running vision language models and omni models that take images, audio, and video on a Mac. It offers a CLI, a Python API, a Gradio chat UI, and an OpenAI-style FastAPI server with continuous batching, prefix caching, KV cache quantization, and speculative decoding. Developers and researchers use it to turn Hugging Face checkpoints into quantized MLX models, do OCR and multimodal chat offline, and fine-tune models on their own hardware.

Images

Facts

Stars
5,641 GitHub stars.
5,641

Forks
845
Commits
1,695
Contributors
180
Language
Python
License
MIT
Last commit
Oct 19, 2026
On GitHub since
April 2024
First release
April 2024
Platforms
macOS, CLI, library
Self-hostable
No
Author
Prince Canuma
Tags
  • llm-inference
  • ocr
  • multimodal
  • local-ai
  • model-optimization
  • fine-tuning

Last synced from GitHub on Oct 20, 2026

The 10 best overlooked open-source projects, every Monday.

Share and more

Comments

No comments yet. Start the conversation.

Similar projects

  • google-ai-edge avatar

    LiteRT-LM

    On-device LLM runtime for phones, desktops, browsers, and IoT boards

    6.7k
  • Hugging Face avatar

    Hugging Face Transformers

    Python library defining pretrained models for text, vision, and audio

    168k
  • Gavin Li avatar

    AirLLM

    Run very large language models on a single low-memory GPU

    39.7k

What people are saying

Updated Oct 21, 2026
  • Hacker NewsMlx-VLM: Fast Local VLMs and Omni Models on Apple Silicon with MLXApr 5, 2026 · 2 points · 0 comments (opens Hacker News in a new tab)