# 429 Errors and Model Overloaded - Dedicated Endpoint

**URL:** <https://discuss.huggingface.co/t/429-errors-and-model-overloaded-dedicated-endpoint/113448>\
**Category:** Inference Endpoints on the Hub\
**Created:** [October 22, 2024, 7:34pm UTC](https://discuss.huggingface.co/t/429-errors-and-model-overloaded-dedicated-endpoint/113448 "2024-10-22T19:34:48Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jamie-de](https://avatars.discourse-cdn.com/v4/letter/j/bcef8e/32.png) [@jamie-de](https://discuss.huggingface.co/u/jamie-de)\
**Post date:** [October 22, 2024, 7:34pm UTC](https://discuss.huggingface.co/t/429-errors-and-model-overloaded-dedicated-endpoint/113448/1 "2024-10-22T19:34:48Z")

</div>

Hi! We have a model that we hit 429 errors on and “Model overloaded” errors. What are the rate limits for a dedicated endpoint? I can’t seem to find that information anywhere. We are using an instance size of:

```auto
GPU · Nvidia L4 · 1x GPU · 24 GB

```