# Install mlx with Homebrew, MacPorts Array framework for Apple silicon. Version 0.31.2 via Homebrew; verified 2026-06-25. ## Install ```sh sudo av install brew:mlx ``` Additional install commands: ### macOS - Homebrew (100%): ```sh brew install mlx ``` Evidence: local Homebrew formula metadata - MacPorts (94%): ```sh sudo port install mlx ``` Evidence: MacPorts ports tree: llm/mlx/Portfile from https://api.github.com/repos/macports/macports-ports/git/trees/master?recursive=1 ## Package facts - **Package key:** brew:mlx - **Package manager:** Homebrew - **Package manager page:** - **Version:** 0.31.2 - **Source summary:** Array framework for Apple silicon - **Homepage:** - **Repository:** - **Upstream docs:** - **License:** MIT AND Apache-2.0 - **Source archive:** - **Last updated:** 2026-06-25T13:37:55+02:00 - **Generated:** 2026-07-08T07:18:31+00:00 ## Executables - mlx.distributed_config (cli) - mlx.launch (cli) - mlx.distributed_config (alias) - mlx.launch (alias) ## Dependencies - python@3.14 ## Build dependencies - cmake - fmt - nanobind - nlohmann-json - python-setuptools - robin-map ## Install behavior - Post-install hook: not defined - Bottle: available on arm64_sequoia, arm64_sonoma, arm64_tahoe ## Freshness - Page generated: 2026-07-08 - Package-manager version: 0.31.2 - Package-manager updated: 2026-06-25 - Local data: ok - Upstream repository: https://github.com/ml-explore/mlx - Upstream latest detected: v0.31.2 (current) ## Project history and usage 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. ### Project history 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. ### How it is used 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 - - - - - - ## Security Notes narrow executable package without higher-risk signals. - **Geiger risk:** green / low - narrow executable package without higher-risk signals ## Source Database Details - **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 ## Other Package-Manager Records - 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 ## Related links - [Source-control packages](https://www.automicvault.com/pkg/source-control-tools/) - Belongs to a source-control command family. - [Terminal utility packages](https://www.automicvault.com/pkg/terminal-utilities/) - Matched terminal and command-line workflow metadata. - [Text processing packages](https://www.automicvault.com/pkg/text-processing-tools/) - Matched text, document, or structured-data processing metadata. - [Developer build packages](https://www.automicvault.com/pkg/developer-build-tools/) - Matched build, compiler, generator, or developer workflow metadata. - [python@3.14](https://www.automicvault.com/pkg/brew/python-3-14/) - Runtime dependency declared by Homebrew. - [cmake](https://www.automicvault.com/pkg/brew/cmake/) - Build dependency declared by Homebrew. - [mlx-lm](https://www.automicvault.com/pkg/brew/mlx-lm/) - Popular package that depends on this formula. - [llama.cpp](https://www.automicvault.com/pkg/brew/llama-cpp/) - Shares av.db curated category or tags: c-plus-plus, cli, developer-tools, machine-learning. - [pytorch](https://www.automicvault.com/pkg/brew/pytorch/) - Shares av.db curated category or tags: cli, developer-tools, machine-learning, python. - [crf++](https://www.automicvault.com/pkg/brew/crf/) - Shares av.db curated category or tags: cli, developer-tools, machine-learning. - [dvc](https://www.automicvault.com/pkg/brew/dvc/) - Shares av.db curated category or tags: cli, developer-tools, machine-learning. - [hf](https://www.automicvault.com/pkg/brew/hf/) - Shares av.db curated category or tags: cli, developer-tools, machine-learning. - [hf-mcp-server](https://www.automicvault.com/pkg/brew/hf-mcp-server/) - Shares av.db curated category or tags: cli, developer-tools, machine-learning. - [text-embeddings-inference](https://www.automicvault.com/pkg/brew/text-embeddings-inference/) - Shares av.db curated category or tags: cli, developer-tools, machine-learning. ## Combined YAML source View the package source record on GitHub. [combined/mlx.yml](https://github.com/automic-vault/db/blob/main/combined/mlx.yml) ## Sources - Nucleus package database - Geiger risk classifier - package-page enrichment - curated package history - package version freshness - av.db category and tag curation - package relationship graph - external package-manager database matches - cross-ecosystem install command graph