# 使用 Homebrew 安装 mlx-lm 查看 mlx-lm 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-lm ``` 其他安装命令: ### macOS - Homebrew (100%): ```sh brew install mlx-lm ``` 证据: local Homebrew formula metadata ## 软件包事实 - **软件包键:** brew:mlx-lm - **软件包管理器:** Homebrew - **软件包管理器页面:** - **版本:** 0.31.3 - **来源摘要:** Run LLMs with MLX - **主页:** - **仓库:** - **许可证:** MIT - **源码归档:** - **最后更新:** 2026-06-20T05:07:43Z - **已生成:** 2026-08-04T22:13:35+00:00 ## 可执行文件 - mlx_lm (cli) - mlx_lm.awq (cli) - mlx_lm.benchmark (cli) - mlx_lm.cache_prompt (cli) - mlx_lm.chat (cli) - mlx_lm.convert (cli) - mlx_lm.dwq (cli) - mlx_lm.dynamic_quant (cli) - mlx_lm.evaluate (cli) - mlx_lm.fuse (cli) - mlx_lm.generate (cli) - mlx_lm.gptq (cli) - mlx_lm.lora (cli) - mlx_lm.manage (cli) - mlx_lm.perplexity (cli) - mlx_lm.server (cli) - mlx_lm.share (cli) - mlx_lm.upload (cli) - mlx_lm (别名) - mlx_lm.awq (别名) - mlx_lm.benchmark (别名) - mlx_lm.cache_prompt (别名) - mlx_lm.chat (别名) - mlx_lm.convert (别名) - mlx_lm.dwq (别名) - mlx_lm.dynamic_quant (别名) - mlx_lm.evaluate (别名) - mlx_lm.fuse (别名) - mlx_lm.generate (别名) - mlx_lm.gptq (别名) - mlx_lm.lora (别名) - mlx_lm.manage (别名) - mlx_lm.perplexity (别名) - mlx_lm.server (别名) - mlx_lm.share (别名) - mlx_lm.upload (别名) ## 依赖 - certifi - libyaml - mlx - numpy - protobuf - python@3.14 - sentencepiece ## 构建依赖 - pkgconf - rust ## 安装行为 - post-install 钩子: 未定义 - 服务: declared - Bottle: 可用 于 arm64_sequoia, arm64_sonoma, arm64_tahoe ## 版本和新鲜度 - 页面生成时间: 2026-08-04 - 管理器版本: 0.31.3 - 管理器更新时间: 2026-06-20 - 本地数据: OK - 上游仓库: https://github.com/ml-explore/mlx-lm - 信息: No cached GitHub release or tag data was available. ## 项目历史与用法 MLX LM is the language-model layer built on top of Apple's MLX array framework. The upstream project describes it as a Python package for generating text and fine-tuning large language models on Apple silicon with MLX. It packages common local-LLM workflows into command-line tools and Python APIs: generation, chat, model conversion, quantization, LoRA and full fine-tuning, benchmarking, prompt caching, upload/share flows, and a local server. ### 项目历史 Its ecosystem role is to make MLX usable for Hugging Face-style LLM work without each user wiring model loading, tokenization, generation loops, quantization, and fine-tuning scripts by hand. The README highlights Hugging Face Hub integration, quantizing and uploading models, low-rank and full fine-tuning with quantized models, and distributed inference and fine-tuning through MLX distributed support. The MLX examples repository points users from earlier LLM examples to MLX LM as the more fully featured package. ### 使用方式 Adoption is tied to the Apple-silicon local-model community. The MLX Community organization on Hugging Face hosts ready-to-use model weights for MLX LM and related MLX projects, and Apple's WWDC material presents MLX LM as the package for running and fine-tuning large language models on Macs. In Homebrew it is a convenience package for users who want the MLX LLM command suite installed as normal CLI tools rather than only through Python packaging. ### 来源 - - - - - ## 安全说明 broad file, network, media, or database tool signal. formula declares a Homebrew service. - **Geiger 风险:** orange / 中 - broad file, network, media, or database tool signal - formula declares a Homebrew service ## 源数据库详情 - **Source Database:** Homebrew formula API - **Tap:** homebrew/core - **Full Name:** mlx-lm - **Version Scheme:** 0 - **Revision:** 2 - **Head Version:** HEAD - **Requirements:** macos - **Bottle Stable Root URL:** - **Deprecated:** no - **Disabled:** no - **Keg Only:** no - **URL Keys:** head, stable ## 相关链接 - [Source-control packages](https://pkg.so/zh-hans/source-control-tools/) - Belongs to a source-control command family. - [MCP tool packages](https://pkg.so/zh-hans/mcp-tools/) - Mentions MCP or Model Context Protocol. - [Secret-risk packages](https://pkg.so/zh-hans/secret-risk-packages/) - Has protected-tool coverage, approval-gate, or non-low Geiger security signals. - [AI and agent packages](https://pkg.so/zh-hans/ai-agent-tools/) - Matched AI model, agent, coding-agent, orchestration, or MCP metadata. - [python@3.14](https://pkg.so/zh-hans/brew/python-3-14/) - Runtime dependency declared by Homebrew. - [protobuf](https://pkg.so/zh-hans/brew/protobuf/) - Runtime dependency declared by Homebrew. - [numpy](https://pkg.so/zh-hans/brew/numpy/) - Runtime dependency declared by Homebrew. - [mlx](https://pkg.so/zh-hans/brew/mlx/) - Runtime dependency declared by Homebrew. - [sentencepiece](https://pkg.so/zh-hans/brew/sentencepiece/) - Runtime dependency declared by Homebrew. - [pkgconf](https://pkg.so/zh-hans/brew/pkgconf/) - Build dependency declared by Homebrew. - [rust](https://pkg.so/zh-hans/brew/rust/) - Build dependency declared by Homebrew. - [llama.cpp](https://pkg.so/zh-hans/brew/llama-cpp/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, model-tools. - [llm](https://pkg.so/zh-hans/brew/llm/) - Shares pkgdb curated category or tags: ai, cli, large-language-models, model-tools. - [ramalama](https://pkg.so/zh-hans/brew/ramalama/) - Shares pkgdb curated category or tags: ai, cli, inference, model-tools. - [localai](https://pkg.so/zh-hans/brew/localai/) - Shares pkgdb curated category or tags: ai, cli, inference, model-tools. - [rapid-mlx](https://pkg.so/zh-hans/brew/rapid-mlx/) - Shares pkgdb curated category or tags: ai, cli, mlx, model-tools. - [djl-serving](https://pkg.so/zh-hans/brew/djl-serving/) - Shares pkgdb curated category or tags: ai, cli, inference, machine-learning, model-serving. - [ollama](https://pkg.so/zh-hans/brew/ollama/) - Shares pkgdb curated category or tags: ai, cli, model-tools. - [llmfit](https://pkg.so/zh-hans/brew/llmfit/) - Shares pkgdb curated category or tags: ai, cli, model-tools. - [oterm](https://pkg.so/zh-hans/brew/oterm/) - Both packages touch the same language runtime or ecosystem. Shared terms: ai, certifi, chat, cli, libyaml. - [pocket-tts](https://pkg.so/zh-hans/brew/pocket-tts/) - Both packages touch the same language runtime or ecosystem. Shared terms: ai, certifi, cli, learning, libyaml. ## Combined YAML source View the package source record on GitHub. [combined/mlx-lm.yml](https://github.com/mxcl/pkgdb/blob/main/combined/mlx-lm.yml) ## 来源 - pkg.so package database - Geiger risk classifier - package-page enrichment - curated package history - package version freshness - pkgdb category and tag curation - package relationship graph - cross-ecosystem install command graph