pkg.soopen package index

cask

Install vmlx with Homebrew Cask

Run local AI models on Apple Silicon. Version 1.6.83 via Homebrew Cask; verified from local package data.

Install commandSecurity notes

install

Additional install commands

macOS

Homebrew Caskverified · 100%
brew install --cask vmlx

local Homebrew cask metadata

overview

Package summary

Run local AI models on Apple Silicon

Commands and aliases

No executable aliases were found in the local package database.

history

Project history and usage

vMLX is a local AI inference engine and macOS desktop application for Apple Silicon. It runs and serves language, vision, embedding, reranking, speech, and image models through OpenAI- and Anthropic-compatible APIs.

Project history

vMLX was created by Jinho Jang/JANGQ AI as an Apple-Silicon inference and model-serving project. It developed into the engine behind a desktop MLX Studio experience, combining chat, model-session management, image generation, conversion tools, and API reference functions.

Adoption history

vMLX is distributed both as a macOS desktop application and a Python package. Its compatibility with OpenAI and Anthropic client protocols lets existing SDKs and agent tools use locally hosted Apple-Silicon models by changing the endpoint rather than adopting a project-specific API.

How it is used

Desktop users download the macOS application, load local models, and manage chat or server sessions from the UI and menu bar. Command-line users install the Python package and invoke commands such as `vmlx serve`, `vmlx convert`, `vmlx info`, `vmlx doctor`, and `vmlx bench`. Existing clients can use the local HTTP endpoint with OpenAI- or Anthropic-compatible SDKs.

Why package nerds care

The project packages an unusually broad local-AI stack—desktop UI, Python inference engine, model conversion, quantization, API serving, and developer tools—around Apple's MLX ecosystem. Package enthusiasts care about it as a Mac-native alternative to general-purpose local model servers and as a way to exploit unified memory, Metal acceleration, and aggressively quantized models.

Timeline

  • 2026: Official project documentation described vMLX as both a Python engine and the backend of a multi-mode MLX Studio desktop application.

Related projects

  • Apple MLX and the mlx-lm/mlx-vlm ecosystem provide core Apple-Silicon model primitives.
  • JANG supplies the project's adaptive mixed-precision quantization format and runtime integration.
  • MLX Studio is the desktop product surface built around vMLX.

security posture

No protected-tool coverage found yet

No matching local secret-handling manifest was found for vmlx. Package metadata is still published here so future coverage has a stable package URL.

Install behavior

  • No Homebrew post-install hook is recorded in formula metadata.
  • No Homebrew bottle metadata was recorded.

Recommended review

Before unattended agent use, check whether the tool reads plaintext credentials, writes remote state, publishes artifacts, or shells out to plugins.

executables

Installed executables

CommandKindExposureNote
No executable data was present.

freshness

Version and freshness

These signals separate page generation age, package-manager activity, and upstream release comparison. Version lag is warned only when an evidence URL and comparable versions are present.

page generated2026-11-04
manager version1.6.83
manager updated
local dataok
upstreamnot checked
latest detectednot detected

https://github.com/jjang-ai/mlxstudio

install metadata

Package metadata

Package keycask:vmlx
Version1.6.83
Package managerHomebrew Cask
Package manager pagehttps://formulae.brew.sh/cask/vmlx
Homepagehttps://mlx.studio/
Repositoryhttps://github.com/jjang-ai/mlxstudio
Upstream docshttps://mlx.studio/
Source archivehttps://github.com/jjang-ai/mlxstudio/releases/download/v1.6.83/vMLX-1.6.83-sequoia-arm64.dmg
SHA-256223c23316cd5ae2440f91dd6a9a37e179f624d1e053cfba375ca68f1da3bf96f
Bottlenot recorded
Homebrew post-installnot defined
Servicenone declared

registry facts

Source database details

Source DatabaseHomebrew cask API
Taphomebrew/cask
Full Tokenvmlx
Names
  • vMLX
Depends On
Arch
{'type': 'arm', 'bits': 64}
Macos
>=: 14
Artifacts
App
1
Target
1
Uninstall
1
Zap
1
Auto Updatesyes
Deprecatedno
Disabledno

package graph

Links come from deterministic package relationships, av.db category and tag curation, ecosystem matches, and package hub membership.

Same workflow

  • ollamaLocal package facts share a topical domain. Shared terms: ai, local, models, run.
  • rapid-mlxLocal package facts share a topical domain. Shared terms: ai, apple, local, silicon.
  • node-llama-cppLocal package facts share a topical domain. Shared terms: ai, local, models, run.

source trail

Generated from repository data

This page is generated by av-web from the private package SQLite artifact built by scripts/generate-pkg-sqlite.py.

Used sources

  • cross-ecosystem install command graph
  • curated package history
  • package relationship graph
  • package version freshness
  • package-page enrichment