// Run models locally
mlx-vlmv0.7.10
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
Open source Maintained For developers
IN ONE PARAGRAPH
mlx-vlm is MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
Good for: Developers and teams who want to run models locally.
01How to start
- 1Read the official quick-start (link above).
- 2Install from the official package registry:
pip install mlx-vlm - 3Try it on a small example before wiring it into a project.
02Alternatives & comparison
Compare side by side → mlx MLX: An array framework for Apple silicon ★ 29k llamafile Distribute and run LLMs with a single file. ★ 26k lmdeploy LMDeploy is a toolkit for compressing, deploying, and serving LLMs. ★ 8.1k gpustack A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances. ★ 5.9k lms LM Studio CLI ★ 5.4k
03Related
- ›Elements of AI · 赫尔辛基大学 / MinnaLearnMultilingual (incl. EN/ZH)
- ›AI For Everyone · DeepLearning.AI / 吴恩达English
- ›Generative AI for Everyone · DeepLearning.AI / 吴恩达English
- ›Introduction to Generative AI 学习路径 · Google Cloud SkillsEnglish
- ›Microsoft Learn: Fundamentals of Generative AI · Microsoft LearnMultilingual (incl. EN/ZH)
- All tutorials →