# Differences Between Space Hardware Configurations and CPU Upgrade Space's 500 Error Issue

**URL:** <https://discuss.huggingface.co/t/differences-between-space-hardware-configurations-and-cpu-upgrade-spaces-500-error-issue/114821>\
**Category:** Spaces\
**Created:** [October 31, 2024, 5:13am UTC](https://discuss.huggingface.co/t/differences-between-space-hardware-configurations-and-cpu-upgrade-spaces-500-error-issue/114821 "2024-10-31T05:13:20Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![bugrase](https://avatars.discourse-cdn.com/v4/letter/b/a3d4f5/32.png) [@bugrase](https://discuss.huggingface.co/u/bugrase)\
**Post date:** [October 31, 2024, 5:13am UTC](https://discuss.huggingface.co/t/differences-between-space-hardware-configurations-and-cpu-upgrade-spaces-500-error-issue/114821/1 "2024-10-31T05:13:20Z")

</div>

Hello,  
I designed a backend for an LLM Leaderboard. The issue is that while it runs on the same space with **CPU basic and Nvidia T4 medium** , _ **it doesn’t work on CPU Upgrade** _. After the model loads, it gives a connection error during the inference phase. I don’t understand why it’s not working on a resource with more RAM and CPU when it works fine on a lower resource. It’s a very frustrating situation. Is there anyone who can help?

here is the space link: [Backend - a Hugging Face Space by LLM-Beetle](https://huggingface.co/spaces/LLM-Beetle/OpenLLM-Azerbaijani-Backend-v1)

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [October 31, 2024, 5:37am UTC](https://discuss.huggingface.co/t/differences-between-space-hardware-configurations-and-cpu-upgrade-spaces-500-error-issue/114821/2 "2024-10-31T05:37:58Z")

</div>

Maybe same here…

> **[@Tonic on Hugging Face: "if you're encountering 500 errors on spaces that...](https://huggingface.co/posts/Tonic/150496682999597)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

---

<div class="post-metadata">

**Author:** ![Majen](https://avatars.discourse-cdn.com/v4/letter/m/7bcc69/32.png) [@Majen](https://discuss.huggingface.co/u/Majen)\
**Post date:** [December 10, 2024, 10:36am UTC](https://discuss.huggingface.co/t/differences-between-space-hardware-configurations-and-cpu-upgrade-spaces-500-error-issue/114821/3 "2024-12-10T10:36:04Z")

</div>

Likely same issue, I am using HF space to prepare dataset, using the CPU Upgrade for 4 spaces and while 2 of them runs just happy, the other 2 with the same CPU Upgrade gets throttled and crash after a certain time perriod

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [December 10, 2024, 10:55am UTC](https://discuss.huggingface.co/t/differences-between-space-hardware-configurations-and-cpu-upgrade-spaces-500-error-issue/114821/4 "2024-12-10T10:55:19Z")

</div>

@meganariley @not-lain Paid space error issue. Apart from the Tonic 500 error, there seems to be a Spaces error that occurs after a certain amount of time. I’ve seen other complaints about the same thing.

Perhaps related:

> [@Preparing space forever](https://discuss.huggingface.co/t/preparing-space-forever/127943):
>
> it works at the beginning button get preparing space forever after 15min. Please help. It is a docker space