# HfHubHTTPError: 503 server error **URL:** \ **Category:** Beginners\ **Created:** [April 17, 2025, 3:47pm UTC](https://discuss.huggingface.co/t/hfhubhttperror-503-server-error/151000 "2025-04-17T15:47:57Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![supratim1034](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/supratim1034/32/45742_2.png) [@supratim1034](https://discuss.huggingface.co/u/supratim1034)\ **Post date:** [April 17, 2025, 3:47pm UTC](https://discuss.huggingface.co/t/hfhubhttperror-503-server-error/151000/1 "2025-04-17T15:47:57Z")
Hi All, I have been going through the new “Agentic AI” course and I am using the notebook here: [dummy\_agent\_library.ipynb · agents-course/notebooks at main](https://huggingface.co/agents-course/notebooks/blob/main/dummy_agent_library.ipynb) Although text generation for “Llama-3.2-3B-Instruct” works without any prompt template, however, with template it fails with 503 error. Any idea what is going wrong here? ---
**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 17, 2025, 4:16pm UTC](https://discuss.huggingface.co/t/hfhubhttperror-503-server-error/151000/2 "2025-04-17T16:16:23Z")
I don’t think there is a problem on your end. There was a major outage a few days ago, and it seems that the Inference API for that model has been turned off since then. > [@Getting "502 Server Error: Bad Gateway for url: https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B-Instruct" error](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740): > > i am accessing llama3.2\_3b instruct model via huggingfacehub. while calling llm.invoke it hangs. Everything was working fine before yesterday ie 15.04.25. Is anyone else also facing this issue. When will this be resolved