# Fine tune large model on a single gpu

**URL:** <https://discuss.huggingface.co/t/fine-tune-large-model-on-a-single-gpu/27003>\
**Category:** Models\
**Created:** [November 30, 2022, 11:27am UTC](https://discuss.huggingface.co/t/fine-tune-large-model-on-a-single-gpu/27003 "2022-11-30T11:27:29Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Imran1](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/imran1/32/18779_2.png) [@Imran1](https://discuss.huggingface.co/u/Imran1)\
**Post date:** [November 30, 2022, 11:27am UTC](https://discuss.huggingface.co/t/fine-tune-large-model-on-a-single-gpu/27003/1 "2022-11-30T11:27:29Z")

</div>

Hi, I want to fine tune large model like gpt-j, mgpt, gpt-neo in colab using single GPU.

Can some one provide me, an example how I can load large model on single gpu to fine tune further for downstream task.