# Use available frameworks and runtimes

<svg xmlns="http://www.w3.org/2000/svg" width="16" height="17" viewbox="0 0 16 17" fill="none" aria-label="icon-book">
<path d="M8 2.5V14.5M3.33333 2.5H12.6667C13.403 2.5 14 3.09695 14 3.83333V13.1667C14 13.903 13.403 14.5 12.6667 14.5H3.33333C2.59695 14.5 2 13.903 2 13.1667V3.83333C2 3.09695 2.59695 2.5 3.33333 2.5Z" stroke="#717171" stroke-width="1.33333" stroke-linecap="round" stroke-linejoin="round"></path>
</svg> Run LiteRT models using delegates and back-ends

Run a LiteRT model using the available delegates and back-ends.

<svg xmlns="http://www.w3.org/2000/svg" width="16" height="17" viewbox="0 0 16 17" fill="none" aria-label="icon-book">
<path d="M8 2.5V14.5M3.33333 2.5H12.6667C13.403 2.5 14 3.09695 14 3.83333V13.1667C14 13.903 13.403 14.5 12.6667 14.5H3.33333C2.59695 14.5 2 13.903 2 13.1667V3.83333C2 3.09695 2.59695 2.5 3.33333 2.5Z" stroke="#717171" stroke-width="1.33333" stroke-linecap="round" stroke-linejoin="round"></path>
</svg> Run an ONNX model on NPU using ORT

Run an ONNX model on the neural processing unit (NPU) using the ONNXX runtime (ORT).

Last Published: May 14, 2026

Previous Topic
 
Fine tune model accuracy with AIMET Next Topic

Run a LiteRT model on supported runtimes