Skip to content

pull command

Download models from URLs

A wrapper around ipull to download model files as fast as possible with parallel connections and other optimizations.

Automatically handles split and binary-split models files, so only pass the URI to the first file of a model.

If a file already exists and its size matches the expected size, it will not be downloaded again unless the --override flag is used.

The supported URI schemes are:

  • HTTP: https://, http://
  • Hugging Face: hf:<user>/<model>/<file-path>#<branch> (#<branch> is optional)

Learn more about using model URIs in the Downloading Models guide.

To programmatically download a model file in your code, use createModelDownloader()

Usage

shell
npx --no node-llama-cpp pull [urls..]

Options

Required

Option Description
--urls [string], --url [string], --uris [string], --uri [string] A .gguf model URI to pull. Pass multiple URIs to download multiple models at once. (string[]) (required)

Optional

Option Description
-H [string], --header [string] Headers to use when downloading a model from a URL, in the format key: value. You can pass this option multiple times to add multiple headers. (string[])
-o, --override Override existing model files (default: false) (boolean)
--noProgress Do not show a progress bar while downloading (default: false) (boolean)
--noTempFile, --noTemp Delete the temporary file when canceling the download (default: false) (boolean)
-d [string], --directory [string], --dir [string] Directory to save the model to (default: ~/.node-llama-cpp/models) (string)
-n [string], --filename [string], --name [string] Filename to save the model as. Can only be used if a single URL is passed (string)
-p <number>, --parallel <number> Maximum parallel downloads (default: 4) (number)

Other

Option Description
-h, --help Show help
-v, --version Show version number