# Quantized Pytorch model exports to onnx

**URL:** <https://discuss.pytorch.org/t/quantized-pytorch-model-exports-to-onnx/144968>\
**Category:** quantization\
**Created:** [February 25, 2022, 12:32am UTC](https://discuss.pytorch.org/t/quantized-pytorch-model-exports-to-onnx/144968 "2022-02-25T00:32:03Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![lyt91222](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/l/439d5e/32.png) [@lyt91222](https://discuss.pytorch.org/u/lyt91222)\
**Post date:** [February 25, 2022, 6:54pm UTC](https://discuss.pytorch.org/t/quantized-pytorch-model-exports-to-onnx/144968/3 "2022-02-25T18:54:08Z")

</div>

Yeah. But I didn’t see that error when I change from ‘fbgemm’ to ‘qnnpack’.

The error I have seen is same as ZyrianovS [post 24](https://discuss.pytorch.org/t/onnx-export-of-quantized-model/76884/24) and [post 25](https://discuss.pytorch.org/t/onnx-export-of-quantized-model/76884/25)

---

_[View the full topic](https://discuss.pytorch.org/t/quantized-pytorch-model-exports-to-onnx/144968)._