# Quantization of Hybrid Pytorch Model

**URL:** <https://discuss.pytorch.org/t/quantization-of-hybrid-pytorch-model/222931>\
**Category:** quantization\
**Created:** [September 8, 2025, 4:47am UTC](https://discuss.pytorch.org/t/quantization-of-hybrid-pytorch-model/222931 "2025-09-08T04:47:22Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Aman\_230](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/aman_230/32/74934_2.png) [@Aman\_230](https://discuss.pytorch.org/u/Aman_230)\
**Post date:** [September 8, 2025, 4:47am UTC](https://discuss.pytorch.org/t/quantization-of-hybrid-pytorch-model/222931/1 "2025-09-08T04:47:22Z")

</div>

Hi,

I hope you are fine and doing well.  
I have a pytorch model consists of Conv + Bi GRU + FC layer.  
I have trained it and generated a pth file.

I want to quantize it, how to proceed? How to specify per channel quantization in Qconfig? And how to decide between symmetric or asymmetric quantization?

Any help will be very appreciable.