# Cannot run dedicated server for interface endpoint

**URL:** <https://discuss.huggingface.co/t/cannot-run-dedicated-server-for-interface-endpoint/127056>\
**Category:** Inference Endpoints on the Hub\
**Created:** [November 23, 2024, 5:24pm UTC](https://discuss.huggingface.co/t/cannot-run-dedicated-server-for-interface-endpoint/127056 "2024-11-23T17:24:36Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Capital-ai](https://avatars.discourse-cdn.com/v4/letter/c/57b2e6/32.png) [@Capital-ai](https://discuss.huggingface.co/u/Capital-ai)\
**Post date:** [November 23, 2024, 5:24pm UTC](https://discuss.huggingface.co/t/cannot-run-dedicated-server-for-interface-endpoint/127056/1 "2024-11-23T17:24:36Z")

</div>

I am trying to run a dedicated endpoint, I tried several models, different instance size, CPU based, GPU based, tried to run it on AWS/Azure/GCP, it fails every single time with the same error:  
Workload evicted, storage limit exceeded (8G)

What am I doing wrong or what do I need to do to be able to run a dedicated interface endpoint because right now it’s unusable.

Thanks to anyone that helps.

---

<div class="post-metadata">

**Author:** ![Capital-ai](https://avatars.discourse-cdn.com/v4/letter/c/57b2e6/32.png) [@Capital-ai](https://discuss.huggingface.co/u/Capital-ai)\
**Post date:** [November 23, 2024, 7:23pm UTC](https://discuss.huggingface.co/t/cannot-run-dedicated-server-for-interface-endpoint/127056/2 "2024-11-23T19:23:45Z")

</div>

Quick update, I got it to run, so it seems like the recommended setup is not even remotely close to be able to run the model…