# Installer mlx avec Homebrew, MacPorts Consultez les chemins d'installation, exécutables, métadonnées et notes de sécurité de mlx pour les workflows d'agents IA. ## installation ```sh sudo av install brew:mlx ``` Commandes d'installation supplémentaires: ### macOS - Homebrew (100%): ```sh brew install mlx ``` Preuve: local Homebrew formula metadata - MacPorts (94%): ```sh sudo port install mlx ``` Preuve: MacPorts ports tree: llm/mlx/Portfile from https://api.github.com/repos/macports/macports-ports/git/trees/master?recursive=1 ## Faits du paquet - **Clé du paquet:** brew:mlx - **Gestionnaire de paquets:** Homebrew - **Page du gestionnaire de paquets:** - **Version:** 0.32.0 - **Résumé source:** Array framework for Apple silicon - **Page d'accueil:** - **Dépôt:** - **Docs amont:** - **Licence:** MIT AND Apache-2.0 - **Archive source:** - **Dernière mise à jour:** 2026-07-08T14:26:04Z - **Généré:** 2026-08-04T22:13:35+00:00 ## exécutables - mlx.distributed_config (cli) - mlx.launch (cli) - mlx.distributed_config (alias) - mlx.launch (alias) ## Dépendances - python@3.14 ## Dépendances de compilation - cmake - fmt - nanobind - nlohmann-json - python-setuptools - robin-map ## Comportement d'installation - hook post-installation: non défini - Bouteille: disponible sur arm64_sequoia, arm64_sonoma, arm64_tahoe ## Version et fraîcheur - page générée: 2026-08-04 - version du gestionnaire: 0.32.0 - gestionnaire mis à jour: 2026-07-08 - données locales: OK - dépôt amont: https://github.com/ml-explore/mlx - dernière version détectée: v0.32.0 (à jour) ## Historique du projet et usages 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. ### Historique du projet 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. ### Modes d'utilisation 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. ### Sources - - - - - - ## Notes de sécurité narrow executable package without higher-risk signals. - **Risque Geiger:** vert / faible - narrow executable package without higher-risk signals ## Détails de la base source - **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 ## Autres enregistrements de gestionnaires de paquets - 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 ## Liens liés - [Source-control packages](https://pkg.so/fr/source-control-tools/) - Belongs to a source-control command family. - [MCP tool packages](https://pkg.so/fr/mcp-tools/) - Mentions MCP or Model Context Protocol. - [AI and agent packages](https://pkg.so/fr/ai-agent-tools/) - Matched AI model, agent, coding-agent, orchestration, or MCP metadata. - [Terminal utility packages](https://pkg.so/fr/terminal-utilities/) - Matched terminal and command-line workflow metadata. - [python@3.14](https://pkg.so/fr/brew/python-3-14/) - Runtime dependency declared by Homebrew. - [cmake](https://pkg.so/fr/brew/cmake/) - Build dependency declared by Homebrew. - [mlx-lm](https://pkg.so/fr/brew/mlx-lm/) - Popular package that depends on this formula. - [rapid-mlx](https://pkg.so/fr/brew/rapid-mlx/) - Popular package that depends on this formula. - [opencv](https://pkg.so/fr/brew/opencv/) - Shares pkgdb curated category or tags: ai, c-plus-plus, cli, machine-learning, ml-tools. - [pytorch](https://pkg.so/fr/brew/pytorch/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, python. - [rgf](https://pkg.so/fr/brew/rgf/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, python. - [tesseract](https://pkg.so/fr/brew/tesseract/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [hf](https://pkg.so/fr/brew/hf/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [libtensorflow](https://pkg.so/fr/brew/libtensorflow/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [sentencepiece](https://pkg.so/fr/brew/sentencepiece/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [lightgbm](https://pkg.so/fr/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) ## Sources - 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