# Question and Answering run time

**URL:** <https://discuss.huggingface.co/t/question-and-answering-run-time/1248>\
**Category:** 🤗Transformers\
**Created:** [September 24, 2020, 1:38pm UTC](https://discuss.huggingface.co/t/question-and-answering-run-time/1248 "2020-09-24T13:38:12Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![mandy-gutter](https://avatars.discourse-cdn.com/v4/letter/m/e9bcb4/32.png) [@mandy-gutter](https://discuss.huggingface.co/u/mandy-gutter)\
**Post date:** [September 24, 2020, 1:38pm UTC](https://discuss.huggingface.co/t/question-and-answering-run-time/1248/1 "2020-09-24T13:38:12Z")

</div>

I am using the Question and Answering model and the run time is about 14 seconds per data point, my project of ~7000 text data samples took around 26 hours.

What is the best run time I can expect? Will this improve in the near future?

---

<div class="post-metadata">

**Author:** ![valhalla](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/valhalla/32/4179_2.png) [@valhalla](https://discuss.huggingface.co/u/valhalla)\
**Post date:** [September 24, 2020, 3:21pm UTC](https://discuss.huggingface.co/t/question-and-answering-run-time/1248/2 "2020-09-24T15:21:29Z")

</div>

Do you think you can provide some more information ?  
Are you using GPU, pipeline, which model are you using etc