IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /max/get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

max list

Lists every pipeline architecture registered with MAX, along with example Hugging Face repository IDs and the data-type encodings each architecture supports. Use this command to discover what you can pass to max serve, max generate, or max encode.

For example, list all available architectures:

max list

The output is grouped by architecture, with the example repos and supported encodings under each entry:

Architecture: Llama3
    Example Huggingface Repo Ids:
        modularai/Llama-3.1-8B-Instruct-GGUF
    Encoding Supported: float32
    Encoding Supported: bfloat16

To get the same information as JSON (for use in scripts or other tooling), pass the --json flag:

max list --json

The JSON output uses the structure {"architectures": {<name>: {"example_repo_ids": [...], "supported_encodings": [...]}}}.

Usageโ€‹

max list [OPTIONS]

Optionsโ€‹

  • --jsonโ€‹

    Print the list of pipelines options in JSON format.

    Default:

    False