From: Neywa-Labs <github.com/Neywa-Labs>Newsgroups: alt.freeweights.toolsSubject:

MLX-VLM

Release: v0.7.12 (2026-11-04)Commit: 7230940License: MIT

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

inference enginev0.7.12releaseMLX-VLMPythonMIT

FactsLicenseMITLanguagePythonKindinference engineRelease2026-11-04PlatformsmacOS (Apple silicon)Links to the projectpermissive

$ pip install -U mlx-vlm

Overview Install Use with Freeweights License Provenance

Overview

Run and fine-tune vision-language models on a Mac with MLX.

Kind: inference engine
License: MIT
Language: Python
Platforms: macOS (Apple silicon)
Latest release: v0.7.12 (2026-11-04)
Repository: Neywa-Labs/mlx-vlm

Topicsapple-siliconflorence2ideficsllavallmlocal-aimlxmolmopaligemmapixtralvision-frameworkvision-language-model

Freeweights links to the project and does not host tool binaries.

Install

$ pip install -U mlx-vlm

$ pip install -U mlx-vlm

Checked against the project's README on 2026-11-14. The project's own instructions win when they differ: install docs

Freeweights links to the project and does not host tool binaries.

Use with Freeweights

Run a catalog model

Download the weights from Freeweights first (HF_ENDPOINT or fw.py), then point the tool at the folder.

Catalog models it can run (47)

License

License: MIT
Class: Permissive

Read the license

Freeweights links to the project and does not host tool binaries.

Provenance

From: Neywa-Labs <github.com/Neywa-Labs>Newsgroups: alt.freeweights.toolsSubject: MLX-VLMRelease: v0.7.12 (2026-11-04)Commit: 7230940License: MIT

Repository: Neywa-Labs/mlx-vlm
Pinned release: v0.7.12, 2026-11-04
Release commit: 7230940302cbe602054650f18a2f77db945bc57a
Default branch: main e267ccf740b8b9dfc4529665b5efd8b9e1eff187
Fetched: 2026-11-14
Takedowns: None.

Freeweights links to the project and does not host tool binaries.

Get it

Install Project repository

Works with

47 catalog models. See the list