mlx-lm

{
  "aliases": [],
  "alternatives": [],
  "build_dependencies": [
    "pkgconf",
    "rust"
  ],
  "categories": [],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [
    "certifi",
    "libyaml",
    "mlx",
    "numpy",
    "protobuf",
    "python@3.14",
    "sentencepiece"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Run LLMs with MLX",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:41:24+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "mlx-lm",
  "github_default_branch": "main",
  "github_last_commit_at": "2026-06-12T22:12:31Z",
  "github_readme_excerpt": "## MLX LM \n\nMLX LM is a Python package for generating text and fine-tuning large language\nmodels on Apple silicon with MLX.\n\nSome key features include:\n\n* Integration with the Hugging Face Hub to easily use thousands of LLMs with a\n  single command. \n* Support for quantizing and uploading models to the Hugging Face Hub.\n* [Low-rank and full model\n  fine-tuning](https://github.com/ml-explore/mlx-lm/blob/main/mlx_lm/LORA.md)\n  with support for quantized models.\n* Distributed inference and fine-tuning with `mx.distributed`\n\nThe easiest way to get started is to install the `mlx-lm` package:\n\n**With `pip`**:\n\n```sh\npip install mlx-lm\n```\n\n**With `conda`**:\n\n```sh\nconda install -c conda-forge mlx-lm\n```\n\n### Quick Start\n\nTo generate text with an LLM use:\n\n```bash\nmlx_lm.generate --prompt \"How tall is Mt Everest?\"\n```\n\nTo chat with an LLM use:\n\n```bash\nmlx_lm.chat\n```\n\nThis will give you a chat REPL that you can use to interact with the LLM. The\nchat context is preserved during the lifetime of the REPL.\n\nCommands in `mlx-lm` typically take command line options which let you specify\nthe model, sampling parameters, and more. Use `-h` to see a list of available\noptions for a command, e.g.:\n\n```bash\nmlx_lm.generate -h\n```\n\nThe default model for generation and chat is\n`mlx-community/Llama-3.2-3B-Instruct-4bit`.  You can specify any MLX-compatible\nmodel with the `--model` flag. Thousands are available in the\n[MLX Community](https://huggingface.co/mlx-community) Hugging Face\norganization.\n\n### Python API\n\nYou can use `mlx-lm` as a module:\n\n```python\nfrom mlx_lm import load, generate\n\nmodel, tokenizer = load(\"mlx-community/Mistral-7B-Instruct-v0.3-4bit\")\n\nprompt = \"Write a story about Einstein\"\n\nmessages = [{\"role\": \"user\", \"content\": prompt}]\nprompt = tokenizer.apply_chat_template(\n    messages, add_generation_prompt=True,\n)\n\ntext = generate(model, tokenizer, prompt=prompt, verbose=True)\n```\n\nTo see a description of all the arguments you can do:\n\n```\n\u003e\u003e\u003e help(generate)\n```\n\nCheck",
  "github_repo": "ml-explore/mlx-lm",
  "github_stars": 5984,
  "github_topics": [
    "llms",
    "mlx"
  ],
  "homepage": "https://github.com/ml-explore/mlx-lm",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 1123,
  "installs_365d": 4964,
  "installs_90d": 2753,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "MIT",
  "llm_generated_at": null,
  "llm_model": null,
  "name": "mlx-lm",
  "oldnames": [],
  "one_liner": null,
  "optional_dependencies": [],
  "rank_30d": 1240,
  "rank_365d": 1943,
  "rank_90d": 1403,
  "raw_hash": "bc4b6acdf4dfde5b",
  "recommended_dependencies": [],
  "revision": 2,
  "ruby_source_path": "Formula/m/mlx-lm.rb",
  "tap": "homebrew/core",
  "test_dependencies": [],
  "uses_from_macos": [],
  "version_head": "HEAD",
  "version_stable": "0.31.3",
  "versioned_formulae": [],
  "why_use_this": null
}