.. _System Requirements & Setup:

System Requirements & Setup
============================

System Requirements
-------------------

For GenAI model compilation and deployment, you only need the **ModelSDK container** from PaletteSDK, not the full PaletteSDK installation. The ModelSDK container needs to be installed on a machine that matches the following requirements.

.. list-table::
  :widths: 30 70
  :header-rows: 1

  * - Parameter
    - Description
  * - **Operating System**
    - Ubuntu 20.04/22.04 LTS or Windows 10/11 or MacOS 12.0 or later.
  * - **Memory**
    - 128GB or more is recommended.
  * - **Storage**
    - 1TB available space preferred.

.. note::

  With 128GB machine, compilation can take several hours to complete depends on the type of model. 64GB may work for models that do not have vision capabilities.

Prerequisites
-------------

- Ensure that the latest :ref:`sima_cli` `version <https://pypi.org/project/sima-cli/#history>`_ is installed in the ModelSDK container.
- Have a valid Developer Portal account to download assets from `docs.sima.ai <https://docs.sima.ai>`_.
- Have a valid Hugging Face account to download open-source models.
- Some models, such as ``google/paligemma``, require accepting a license agreement on Hugging Face. Make sure to review and accept the license before attempting to download these models.
- Authorize the CLI to access Hugging Face using an `user access token <https://huggingface.co/docs/hub/en/security-tokens>`_ and ``huggingface-cli``. Note, installing ``sima-cli`` automatically installs ``huggingface-cli``.