# Export fp16 model to ONNX

**URL:** <https://discuss.pytorch.org/t/export-fp16-model-to-onnx/87901>\
**Category:** quantization\
**Created:** [July 4, 2020, 1:59am UTC](https://discuss.pytorch.org/t/export-fp16-model-to-onnx/87901 "2020-07-04T01:59:18Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![addisonklinke](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/addisonklinke/32/79137_2.png) [@addisonklinke](https://discuss.pytorch.org/u/addisonklinke)\
**Post date:** [June 17, 2021, 2:30pm UTC](https://discuss.pytorch.org/t/export-fp16-model-to-onnx/87901/2 "2021-06-17T14:30:53Z")

</div>

Most discussion around quantized exports that I’ve found is on this [thread](https://discuss.pytorch.org/t/onnx-export-of-quantized-model/76884/20). However, most users are talking about int8 not fp16 - I’m not sure how similar the approaches/issues are between the two precisions

---

_[View the full topic](https://discuss.pytorch.org/t/export-fp16-model-to-onnx/87901)._