# mlx mit Homebrew, MacPorts installieren Prüfe Installationswege, Executables, Metadaten und Sicherheitshinweise für mlx in AI-Agent-Workflows. ## Installation ```sh sudo av install brew:mlx ``` Weitere Installationsbefehle: ### macOS - Homebrew (100%): ```sh brew install mlx ``` Evidenz: local Homebrew formula metadata - MacPorts (94%): ```sh sudo port install mlx ``` Evidenz: MacPorts ports tree: llm/mlx/Portfile from https://api.github.com/repos/macports/macports-ports/git/trees/master?recursive=1 ## Paketfakten - **Paketschlüssel:** brew:mlx - **Paketmanager:** Homebrew - **Paketmanager-Seite:** - **Version:** 0.32.0 - **Quellzusammenfassung:** Array framework for Apple silicon - **Homepage:** - **Repository:** - **Upstream-Dokumentation:** - **Lizenz:** MIT AND Apache-2.0 - **Quellarchiv:** - **Zuletzt aktualisiert:** 2026-07-08T14:26:04Z - **Generiert:** 2026-08-04T22:13:35+00:00 ## Executables - mlx.distributed_config (cli) - mlx.launch (cli) - mlx.distributed_config (Alias) - mlx.launch (Alias) ## Abhängigkeiten - python@3.14 ## Build-Abhängigkeiten - cmake - fmt - nanobind - nlohmann-json - python-setuptools - robin-map ## Installationsverhalten - Post-install-Hook: nicht definiert - Bottle: verfügbar auf arm64_sequoia, arm64_sonoma, arm64_tahoe ## Version und Aktualität - Seite generiert: 2026-08-04 - Manager-Version: 0.32.0 - Manager aktualisiert: 2026-07-08 - lokale Daten: OK - Upstream-Repository: https://github.com/ml-explore/mlx - neueste erkannte Version: v0.32.0 (aktuell) ## Projektgeschichte und Nutzung 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. ### Projektgeschichte 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. ### Wie es verwendet wird 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. ### Quellen - - - - - - ## Sicherheitshinweise narrow executable package without higher-risk signals. - **Geiger-Risiko:** grün / niedrig - narrow executable package without higher-risk signals ## Details aus der Quelldatenbank - **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 ## Andere Paketmanager-Einträge - 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 ## Verwandte Links - [Source-control packages](https://pkg.so/de/source-control-tools/) - Belongs to a source-control command family. - [MCP tool packages](https://pkg.so/de/mcp-tools/) - Mentions MCP or Model Context Protocol. - [AI and agent packages](https://pkg.so/de/ai-agent-tools/) - Matched AI model, agent, coding-agent, orchestration, or MCP metadata. - [Terminal utility packages](https://pkg.so/de/terminal-utilities/) - Matched terminal and command-line workflow metadata. - [python@3.14](https://pkg.so/de/brew/python-3-14/) - Runtime dependency declared by Homebrew. - [cmake](https://pkg.so/de/brew/cmake/) - Build dependency declared by Homebrew. - [mlx-lm](https://pkg.so/de/brew/mlx-lm/) - Popular package that depends on this formula. - [rapid-mlx](https://pkg.so/de/brew/rapid-mlx/) - Popular package that depends on this formula. - [opencv](https://pkg.so/de/brew/opencv/) - Shares pkgdb curated category or tags: ai, c-plus-plus, cli, machine-learning, ml-tools. - [pytorch](https://pkg.so/de/brew/pytorch/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, python. - [rgf](https://pkg.so/de/brew/rgf/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, python. - [tesseract](https://pkg.so/de/brew/tesseract/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [hf](https://pkg.so/de/brew/hf/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [libtensorflow](https://pkg.so/de/brew/libtensorflow/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [sentencepiece](https://pkg.so/de/brew/sentencepiece/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools. - [lightgbm](https://pkg.so/de/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) ## Quellen - 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