# Inference API returns 504 error for Llama-3.2-3B-Instruct & google/gemma-2-2b-it

**URL:** <https://discuss.huggingface.co/t/inference-api-returns-504-error-for-llama-3-2-3b-instruct-google-gemma-2-2b-it/151440>\
**Category:** Inference Endpoints on the Hub\
**Created:** [April 20, 2025, 3:18pm UTC](https://discuss.huggingface.co/t/inference-api-returns-504-error-for-llama-3-2-3b-instruct-google-gemma-2-2b-it/151440 "2025-04-20T15:18:38Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![aisvarya-adeseye](https://avatars.discourse-cdn.com/v4/letter/a/49beb7/32.png) [@aisvarya-adeseye](https://discuss.huggingface.co/u/aisvarya-adeseye)\
**Post date:** [April 20, 2025, 3:18pm UTC](https://discuss.huggingface.co/t/inference-api-returns-504-error-for-llama-3-2-3b-instruct-google-gemma-2-2b-it/151440/1 "2025-04-20T15:18:38Z")

</div>

Llama used to work for me, but it suddenly stops working, I have not exhausted my inference endpoint limit and I have been granted access by Llama to access the model. The gemma has the same issue

---

<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:** [April 21, 2025, 1:37am UTC](https://discuss.huggingface.co/t/inference-api-returns-504-error-for-llama-3-2-3b-instruct-google-gemma-2-2b-it/151440/2 "2025-04-21T01:37:56Z")

</div>

It’s been like this for a while now. Probably everyone.

> [@Constant 503 error for several days when running LLAMA 3.1](https://discuss.huggingface.co/t/constant-503-error-for-several-days-when-running-llama-3-1/105144):
>
> Hi all. Earlier this month I wrote a script incorporating LLAMA 3.1, and it worked well (with timeouts, etc), but for the past week whenever I try to access LLAMA 3.1 at all I get a 503 error (including for short simple requests, like HF’s sample code). Any idea what the problem may be? I do indeed have Pro.

---

<div class="post-metadata">

**Author:** ![aisvarya-adeseye](https://avatars.discourse-cdn.com/v4/letter/a/49beb7/32.png) [@aisvarya-adeseye](https://discuss.huggingface.co/u/aisvarya-adeseye)\
**Post date:** [April 21, 2025, 6:32am UTC](https://discuss.huggingface.co/t/inference-api-returns-504-error-for-llama-3-2-3b-instruct-google-gemma-2-2b-it/151440/3 "2025-04-21T06:32:46Z")

</div>

I see. Thanks for the info.

---

<div class="post-metadata">

**Author:** ![sxruh](https://avatars.discourse-cdn.com/v4/letter/s/0ea827/32.png) [@sxruh](https://discuss.huggingface.co/u/sxruh)\
**Post date:** [April 21, 2025, 6:40am UTC](https://discuss.huggingface.co/t/inference-api-returns-504-error-for-llama-3-2-3b-instruct-google-gemma-2-2b-it/151440/4 "2025-04-21T06:40:57Z")

</div>

Also getting this 503 error when running /black-forest-labs/FLUX.1-schnell
