# Quantization of Transformers model

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fquantization-of-transformers-model%2F89220%3E%5C
**Category:** 🤗Transformers\
**Created:** [May 29, 2024, 3:28pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fquantization-of-transformers-model%2F89220 "2024-05-29T15:28:54Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![fairp](https://avatars.discourse-cdn.com/v4/letter/f/2acd7d/32.png) [@fairp](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ffairp)%5C
**Post date:** [May 29, 2024, 3:28pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fquantization-of-transformers-model%2F89220%2F1 "2024-05-29T15:28:54Z")

</div>

Which is the best way to quantize a sentence transformer model in your opinion. I am referring to multilingual bert-based models.