For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Install MAX
You can install MAX with a Python or Conda package manager on any supported system.
- pixi
- uv
-
If needed, install
pixi:curl -fsSL https://pixi.sh/install.sh | sh -
Create a project:
pixi init example-project \ -c https://conda.modular.com/max-nightly/ -c conda-forge \ && cd example-project -
Install
max-all:pixi add max-all -
Start the virtual environment:
pixi shell -
Verify the installation:
max --version
-
If needed, install
uv:curl -LsSf https://astral.sh/uv/install.sh | sh -
Create a project:
uv init example-project && cd example-project -
Create and start a virtual environment:
uv venv && source .venv/bin/activate -
Install
max[all]:uv add "max[all]" \ --index https://whl.modular.com/nightly/simple/ \ --prerelease allow -
Verify the installation:
max --version
These commands install the nightly build, which isn't complete and might have new bugs. If you instead want the stable build, switch to the stable docs.
Next steps
Now that you've installed MAX, pick where to start:
- Quickstart: Serve an LLM with an OpenAI-compatible endpoint and then benchmark it.
- Model development overview: Learn how to bring a trained model from Hugging Face to MAX.
- Get started with GPU programming: Learn the basics of GPU programming with Mojo.