> ## Documentation Index
> Fetch the complete documentation index at: https://dragonwingdocs.qualcomm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Prepare a GenAI model

> Prepare a generative AI (GenAI) model for deployment on Qualcomm Dragonwing IoT platforms using Qualcomm AI Hub or Qualcomm Jupyter notebooks.

To prepare a GenAI model for execution on Qualcomm® Dragonwing™ IQ series
evaluation kits, use [Qualcomm AI Hub](https://aihub.qualcomm.com/iot/models)
to export model binaries from a model with precomputed encodings or
[Qualcomm Jupyter notebooks](https://qpm.qualcomm.com/#/main/tools/details/Tutorial_for_LLaVA1_5_7b_IoT)
to generate model binaries from a pre-trained model.

<Note>
  For more Jupyter notebook examples, go to [Qualcomm Package Manager](https://qpm.qualcomm.com/#/main/home),
  select **Tools**, and search for **Generative AI Tutorials**.

  <img src="https://mintcdn.com/qualcomm-prod/WwC9kmcnKl9Ef7de/Key-Documents/AI-Developer-Workflow/_images/qpm-jupyter-notebooks.png?fit=max&auto=format&n=WwC9kmcnKl9Ef7de&q=85&s=26b4d17c563c881ce91e0431f596b658" width="2393" height="870" data-path="Key-Documents/AI-Developer-Workflow/_images/qpm-jupyter-notebooks.png" />
</Note>

The following image shows the preparation process and base system requirements
for both options.

<img src="https://mintcdn.com/qualcomm-prod/L-jqwrTTz49ZAgVX/Key-Documents/AI-Developer-Workflow/_images/genai-model-preparation.png?fit=max&auto=format&n=L-jqwrTTz49ZAgVX&q=85&s=13e0f80edbcd0a5b02130fd3caedafc1" alt="GenAI model preparation process and system requirements for AI Hub and Jupyter notebook options" width="2933" height="1212" data-path="Key-Documents/AI-Developer-Workflow/_images/genai-model-preparation.png" />

Qualcomm AI Model Efficiency Toolkit (AIMET) supports advanced quantization techniques.
Depending on the model used, you may need to choose a different quantization technique
for better accuracy.

The following table summarizes approaches to GenAI model preparation.

| Feature                  | AI Hub                                              | Jupyter notebooks                                           |
| ------------------------ | --------------------------------------------------- | ----------------------------------------------------------- |
| Automation               | High: One command export                            | Medium: Step-by-step process guided by Jupyter notebook     |
| Customization            | Limited: Only applicable to models hosted on AI Hub | High: Full control over quantization and graph optimization |
| Target audience          | Users seeking quick deployment                      | Researchers and advanced users                              |
| Host system requirements | Medium: 80 GB RAM + swap space                      | High: High-End GPU like A100 and RAM + swap space           |