# Slow speed with large context

**URL:** <https://discuss.huggingface.co/t/slow-speed-with-large-context/99170>\
**Category:** 🤗Transformers\
**Created:** [July 24, 2024, 2:19pm UTC](https://discuss.huggingface.co/t/slow-speed-with-large-context/99170 "2024-07-24T14:19:20Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![owaisorakzai](https://avatars.discourse-cdn.com/v4/letter/o/c0e974/32.png) [@owaisorakzai](https://discuss.huggingface.co/u/owaisorakzai)\
**Post date:** [July 24, 2024, 2:19pm UTC](https://discuss.huggingface.co/t/slow-speed-with-large-context/99170/1 "2024-07-24T14:19:20Z")

</div>

Hello everyone. I am using ibm granite 20b model for code generation task, its working pretty good but when I make my prompt and examples in prompt longer, it gets very slow… Can anyone tell how can I make it faster with longer prompts. I have already applied quantization etc