# Mistral from Huggingface is slow

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmistral-from-huggingface-is-slow%2F62771%3E%5C
**Category:** 🤗Transformers\
**Created:** [November 19, 2023, 6:10pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmistral-from-huggingface-is-slow%2F62771 "2023-11-19T18:10:05Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sayan01](https://avatars.discourse-cdn.com/v4/letter/s/48db29/32.png) [@Sayan01](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSayan01)%5C
**Post date:** [November 19, 2023, 6:10pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmistral-from-huggingface-is-slow%2F62771%2F1 "2023-11-19T18:10:05Z")

</div>

I was trying to run a distillation on the Mistral model. I am using the Huggingface version with flash attention. The model is running exceptionally slow. The GPUs are stuck at 0% utilization. Is it normal?

 ![Screen Shot 2023-11-20 at 5.05.53 AM](https://us1.discourse-cdn.com/hellohellohello/original/3X/a/4/a4b578cd45e84d1134a109a3a91b2956999155dd.png)