# 使用 Homebrew, MacPorts 安装 mlx

查看 mlx 的安装路径、可执行文件、元数据以及面向 AI 代理工作流的安全说明。

## 安装

```sh
sudo av install brew:mlx
```

其他安装命令:

### macOS

- Homebrew (100%):

```sh
brew install mlx
```

  证据: local Homebrew formula metadata

- MacPorts (94%):

```sh
sudo port install mlx
```

  证据: MacPorts ports tree: llm/mlx/Portfile from https://api.github.com/repos/macports/macports-ports/git/trees/master?recursive=1

## 软件包事实

- **软件包键:** brew:mlx
- **软件包管理器:** Homebrew
- **版本:** 0.32.0
- **来源摘要:** Array framework for Apple silicon
- **主页:** <https://ml-explore.github.io/mlx/build/html/index.html>
- **仓库:** <https://github.com/ml-explore/mlx>
- **最后更新:** 2026-07-08T14:26:04Z
- **已生成:** 2026-08-03T19:37:03+00:00

## 可执行文件

- mlx.distributed_config (别名)
- mlx.launch (别名)

## 安装行为

- Bottle: 不可用

## 版本和新鲜度

- 页面生成时间: 2026-08-03
- 管理器版本: 0.32.0
## 项目历史与用法

MLX is Apple's open source array framework for machine learning on Apple silicon. The project is published under the ml-explore organization and is described by Apple and the upstream README as an array framework optimized for Apple silicon and its unified memory architecture. The MLX examples citation credits the initial software suite to Awni Hannun, Jagrit Digani, Angelos Katharopoulos, and Ronan Collobert, with a 2023 citation entry.

### 项目历史

Technically, MLX sits in the NumPy, PyTorch, JAX, and ArrayFire family rather than being only a model runner. Its README emphasizes familiar NumPy-like APIs, C, C++, and Swift bindings, PyTorch-like higher-level neural-network and optimizer packages, composable transformations for automatic differentiation and vectorization, lazy computation, dynamic graph construction, CPU/GPU execution, and unified memory so arrays can be operated on across supported devices without explicit transfers.

### 使用方式

The framework quickly became the base layer for a cluster of Apple-silicon ML tools: MLX LM for language models, MLX examples for reference implementations across text, image, audio, video, and multimodal models, and community-converted model weights on Hugging Face. LM Studio also shipped an MLX engine for on-device LLM use on Apple-silicon Macs. In package managers, the `mlx` package is the foundation dependency; users install higher-level packages such as `mlx-lm` when they want complete model workflows.

### 来源

- <https://formulae.brew.sh/formula/mlx>
- <https://github.com/ml-explore/mlx>
- <https://github.com/ml-explore/mlx-examples>
- <https://lmstudio.ai/blog/lmstudio-v0.3.4>
- <https://ml-explore.github.io/mlx/build/html/usage/unified_memory.html>
- <https://opensource.apple.com/projects/mlx>


## 安全说明

narrow executable package without higher-risk signals.

- **Geiger 风险:** 绿色 / 低
- narrow executable package without higher-risk signals

## 其他软件包管理器记录

- MacPorts - mlx: normalized package name match | MacPorts ports tree: llm/mlx/Portfile from https://api.github.com/repos/macports/macports-ports/git/trees/master?recursive=1


## Combined YAML source

View the package source record on GitHub. [combined/mlx.yml](https://github.com/mxcl/pkgdb/blob/main/combined/mlx.yml)


## 来源

- pkg.so package database
- Geiger risk classifier
- curated package history
- pkgdb category and tag curation
- external package-manager database matches
- cross-ecosystem install command graph