# Clarification regarding Quantization in ExecuTorch

**URL:** <https://dev-discuss.pytorch.org/t/clarification-regarding-quantization-in-executorch/2594>\
**Category:** ExecuTorch\
**Created:** [November 15, 2024, 2:46am UTC](https://dev-discuss.pytorch.org/t/clarification-regarding-quantization-in-executorch/2594 "2024-11-15T02:46:52Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![rohit-kumar-manav](https://yyz2.discourse-cdn.com/flex036/user_avatar/dev-discuss.pytorch.org/rohit-kumar-manav/32/1933_2.png) [@rohit-kumar-manav](https://dev-discuss.pytorch.org/u/rohit-kumar-manav)\
**Post date:** [November 15, 2024, 2:46am UTC](https://dev-discuss.pytorch.org/t/clarification-regarding-quantization-in-executorch/2594/1 "2024-11-15T02:46:52Z")

</div>

Hi ExecuTorch Team,

 ![image](https://canada1.discourse-cdn.com/flex036/uploads/pytorch1/original/2X/b/bca49e343db78f14777a3c1ebc6552b70a6a17c4.jpeg)

In ExecuTorch stack as part of Program Preparation, we have optional quantization step.  
If want to plug in our own quantization mechanism, is there any customization entry points for that?  
Please guide if possible, how we can achieve this?

---

<div class="post-metadata">

**Author:** ![mergennachin](https://yyz2.discourse-cdn.com/flex036/user_avatar/dev-discuss.pytorch.org/mergennachin/32/2407_2.png) [@mergennachin](https://dev-discuss.pytorch.org/u/mergennachin)\
**Post date:** [December 2, 2024, 4:02pm UTC](https://dev-discuss.pytorch.org/t/clarification-regarding-quantization-in-executorch/2594/2 "2024-12-02T16:02:39Z")

</div>

Hi @rohit-kumar-manav

Yes, you can write a custom quantizer based on your capability of your backend.

Here are some references:

[https://pytorch.org/executorch/stable/quantization-overview.html](https://pytorch.org/executorch/stable/quantization-overview.html)  
[https://pytorch.org/tutorials/prototype/pt2e\_quantizer.html](https://pytorch.org/tutorials/prototype/pt2e_quantizer.html)