# GPU quota exceeded even when using access token from PRO

**URL:** <https://discuss.huggingface.co/t/gpu-quota-exceeded-even-when-using-access-token-from-pro/90817>\
**Category:** Beginners\
**Created:** [June 7, 2024, 5:58am UTC](https://discuss.huggingface.co/t/gpu-quota-exceeded-even-when-using-access-token-from-pro/90817 "2024-06-07T05:58:44Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![AryanChandwani](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/aryanchandwani/32/27926_2.png) [@AryanChandwani](https://discuss.huggingface.co/u/AryanChandwani)\
**Post date:** [June 7, 2024, 5:58am UTC](https://discuss.huggingface.co/t/gpu-quota-exceeded-even-when-using-access-token-from-pro/90817/1 "2024-06-07T05:58:44Z")

</div>

Hi i keep getting this error in my pycharm console : “The upstream Gradio app has raised an exception: ‘You have exceeded your GPU quota (23s left vs. 60s requested). Please retry in 0:25:06’”

I’m using this  
client = Client(“yisol/IDM-VTON”, hf\_token = ‘’)

Please help me resolve this

---

<div class="post-metadata">

**Author:** ![arnoldmatt](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/arnoldmatt/32/27817_2.png) [@arnoldmatt](https://discuss.huggingface.co/u/arnoldmatt)\
**Post date:** [June 7, 2024, 8:02am UTC](https://discuss.huggingface.co/t/gpu-quota-exceeded-even-when-using-access-token-from-pro/90817/2 "2024-06-07T08:02:32Z")

</div>

Have you tried reducing the requested GPU time by adjusting the timeout parameter in your Client call? This might help you stay within the quota.

If you’re open to exploring alternatives, there could be CPU-compatible versions of the model available or other models that achieve similar results.