# FAQs

> 
> 
> - **Which Python version is supported?**
> 
>     - For python versions please refer to [QNN Setup section](https://docs.qualcomm.com/doc/80-63442-10/topic/windows_setup.html).
> - **Does NPU/HTP only support quantized models.**
> 
> 
> 
> > 
> > 
> > - No, it’s not mandatory to perform quantization while executing a model on the NPU. If not quantized, the precision is FP16.
> - **Which all quantization options are supported by NPU?**
> 
> 
> 
> > 
> > 
> > - By default it’s INT8. You can change it to INT16 while converting by adding parameters `“--act_bw 16”` and/or `“--weight_bw 16”` .
> - **What is the powershell CLI command to download QAIRT SDK?**
> 
> 
> 
> > 
> > 
> > curl.exe -L -o v2.42.0.251225.zip https://apigwx-aws.qualcomm.com/qsc/public/v1/api/download/software/sdks/Qualcomm_AI_Runtime_Community/All/2.42.0.251225/v2.42.0.251225.zip
> >         Copy to clipboard
> 
> 
> 
>     User can change the version number (2.42.0.251225) to download the desired QAIRT SDK.
> - **What are the profiling and debug tools supported by QAIRT SDK?**
> 
> 
> 
> > 
> > 
> > - Other tools include qnn-profile-viewer to check timings of execution of model, qnn-platform-validator to validate the compatibility and configuration of the platform for running AI models, qnn-throughput-net-run to measure and optimize the throughput performance of AI models on Qualcomm® Snapdragon X and X2 platforms, and qnn-accuracy-debugger to debug and improve the accuracy of their AI models. This [page](https://docs.qualcomm.com/doc/80-63442-10/topic/general_tools.html) lists and describes the various SDK tools for Windows developers.
> - **Where do I find more information on Qualcomm® AI RunTime SDK?**
> 
> 
> 
> > 
> > 
> > - See the [AI Runtime SDK documentation](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html) .

Last Published: Jun 16, 2026

[Previous Topic
QAIRT Visualizer](https://docs.qualcomm.com/bundle/publicresource/80-62010-1/topics/qairt-visualizer.md) [Next Topic
Generative AI](https://docs.qualcomm.com/bundle/publicresource/80-62010-1/topics/gen-ai-llm.md)