# mlx を Homebrew, MacPorts でインストール mlx のインストール経路、実行ファイル、メタデータ、AI エージェント向けセキュリティノートを確認します。 ## インストール ```sh sudo av install brew:mlx ``` 追加のインストールコマンド: ### macOS - Homebrew (100%): ```sh brew install mlx ``` 証拠: local Homebrew formula metadata - MacPorts (94%): ```sh sudo port install mlx ``` 証拠: MacPorts ports tree: llm/mlx/Portfile from https://api.github.com/repos/macports/macports-ports/git/trees/master?recursive=1 ## パッケージ情報 - **パッケージキー:** brew:mlx - **パッケージマネージャ:** Homebrew - **パッケージマネージャページ:** - **バージョン:** 0.32.0 - **ソース概要:** Array framework for Apple silicon - **ホームページ:** - **リポジトリ:** - **上流ドキュメント:** - **ライセンス:** MIT AND Apache-2.0 - **ソースアーカイブ:** - **最終更新:** 2026-07-08T14:26:04Z - **生成日時:** 2026-08-04T22:13:35+00:00 ## 実行可能ファイル - mlx.distributed_config (cli) - mlx.launch (cli) - mlx.distributed_config (エイリアス) - mlx.launch (エイリアス) ## 依存関係 - python@3.14 ## ビルド依存関係 - cmake - fmt - nanobind - nlohmann-json - python-setuptools - robin-map ## インストール挙動 - post-install フック: 未定義 - Bottle: 利用可能 対象 arm64_sequoia, arm64_sonoma, arm64_tahoe ## バージョンと鮮度 - ページ生成日: 2026-08-04 - マネージャ版: 0.32.0 - マネージャ更新日: 2026-07-08 - ローカルデータ: OK - 上流リポジトリ: https://github.com/ml-explore/mlx - 検出された最新: v0.32.0 (最新) ## プロジェクトの歴史と使われ方 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. ### プロジェクトの歴史 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. ### 使われ方 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. ### ソース - - - - - - ## セキュリティノート narrow executable package without higher-risk signals. - **Geiger リスク:** グリーン / 低 - narrow executable package without higher-risk signals ## ソースデータベース詳細 - **Source Database:** Homebrew formula API - **Tap:** homebrew/core - **Full Name:** mlx - **Version Scheme:** 0 - **Revision:** 0 - **Head Version:** HEAD - **Requirements:** arch, macos, xcode - **Bottle Stable Root URL:** - **Deprecated:** no - **Disabled:** no - **Keg Only:** no - **URL Keys:** head, stable ## 他のパッケージマネージャ記録 - 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 ## 関連リンク - [Source-control packages](https://pkg.so/ja/source-control-tools/) - Belongs to a source-control command family. - [MCP tool packages](https://pkg.so/ja/mcp-tools/) - Mentions MCP or Model Context Protocol. - [AI and agent packages](https://pkg.so/ja/ai-agent-tools/) - Matched AI model, agent, coding-agent, orchestration, or MCP metadata. - [Terminal utility packages](https://pkg.so/ja/terminal-utilities/) - Matched terminal and command-line workflow metadata. - [python@3.14](https://pkg.so/ja/brew/python-3-14/) - Runtime dependency declared by Homebrew. - [cmake](https://pkg.so/ja/brew/cmake/) - Build dependency declared by Homebrew. - [mlx-lm](https://pkg.so/ja/brew/mlx-lm/) - Popular package that depends on this formula. - [rapid-mlx](https://pkg.so/ja/brew/rapid-mlx/) - Popular package that depends on this formula. - [opencv](https://pkg.so/ja/brew/opencv/) - Shares pkgdb curated category or tags: ai, c-plus-plus, cli, machine-learning, ml-tools. - [pytorch](https://pkg.so/ja/brew/pytorch/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, python. - [rgf](https://pkg.so/ja/brew/rgf/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, python. - [tesseract](https://pkg.so/ja/brew/tesseract/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [hf](https://pkg.so/ja/brew/hf/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [libtensorflow](https://pkg.so/ja/brew/libtensorflow/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [sentencepiece](https://pkg.so/ja/brew/sentencepiece/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [lightgbm](https://pkg.so/ja/brew/lightgbm/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. ## Combined YAML source View the package source record on GitHub. [combined/mlx.yml](https://github.com/mxcl/pkgdb/blob/main/combined/mlx.yml) ## ソース - pkg.so package database - Geiger risk classifier - package-page enrichment - curated package history - package version freshness - pkgdb category and tag curation - package relationship graph - external package-manager database matches - cross-ecosystem install command graph