> ## 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 your model

> Prepare an AI model for deployment on Qualcomm Dragonwing IoT platforms. Convert, quantize, compile, or fine-tune it using AI Hub, the QAIRT SDK, AIMET, or Edge Impulse.

This is the **prepare-your-model** step of the [Choose your journey](../topic/ai-ml-developer-workflow) flow. Before a model runs efficiently on Qualcomm hardware it is converted to an executable format and, for the Hexagon NPU (HTP), quantized to a supported precision. Qualcomm provides several tools to download a preoptimized model, convert and compile your own, fine-tune with custom data, or recover accuracy lost to quantization.

Select the tool that matches your starting point.

<CardGroup cols={2}>
  <Card title="Use AI Hub to optimize an AI model" icon="download" href="../topic/ai-hub">
    Download a preoptimized model, or bring your own and have it compiled, converted, and quantized in the cloud with Qualcomm AI Hub.
  </Card>

  <Card title="Use Qualcomm AI Runtime SDK to optimize an AI model" icon="gears" href="../topic/qairt">
    Convert, quantize, and compile your own models locally with the Qualcomm AI Runtime (QAIRT) SDK.
  </Card>

  <Card title="Recover accuracy with Qualcomm AI Model Efficiency Toolkit (AIMET)" icon="sliders" href="../topic/aimet">
    Recover accuracy lost during quantization using post-training quantization (PTQ) and quantization-aware training (QAT).
  </Card>

  <Card title="Fine-tune an AI model with custom data using Edge Impulse" icon="bullseye" href="../topic/edge-impulse">
    Build, train, or fine-tune models from your own audio, image, and sensor data with Edge Impulse.
  </Card>
</CardGroup>

<Note>
  Already have a ready-to-run model? You can download a [preoptimized LiteRT model](../topic/ai-hub#try-a-preoptimized-model) from AI Hub and skip straight to [Run inference](../map/use-available-frameworks-and-runtimes).
</Note>