# LLAMA2 70b Inference api stuck on currently loading

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama2-70b-inference-api-stuck-on-currently-loading%2F62152%3E%5C
**Category:** Inference Endpoints on the Hub\
**Created:** [November 14, 2023, 4:10am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama2-70b-inference-api-stuck-on-currently-loading%2F62152 "2023-11-14T04:10:23Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![prapti19](https://avatars.discourse-cdn.com/v4/letter/p/9d8465/32.png) [@prapti19](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fprapti19)%5C
**Post date:** [November 14, 2023, 4:10am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama2-70b-inference-api-stuck-on-currently-loading%2F62152%2F1 "2023-11-14T04:10:23Z")

</div>

Hi,  
Up until till morning, I was using the inference APIs for llama-2-70b-chat-hf model , and now I only get the following error repetatedly:  
`{'error': 'Model meta-llama/Llama-2-70b-chat-hf is currently loading', 'estimated_time': 5518.13232421875}`  
The estimated time does not change as this error keeps on coming. I even tried periodically with a gap of few hours throughout the day, but still with no progress. When I run llama2-7b and llama2-17b its working fine, but for my research project I have to use 70b llama necessarily. Is anyone else facing this problem. Any help will be highly appreciated.

Thanks

P.S. I have bought the Pro membership of HF

---

<div class="post-metadata">

**Author:** ![eboraks](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/eboraks/32/19060_2.png) [@eboraks](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Feboraks)%5C
**Post date:** [November 14, 2023, 10:39am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama2-70b-inference-api-stuck-on-currently-loading%2F62152%2F2 "2023-11-14T10:39:31Z")

</div>

I have the same issue.

---

<div class="post-metadata">

**Author:** ![eboraks](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/eboraks/32/19060_2.png) [@eboraks](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Feboraks)%5C
**Post date:** [November 14, 2023, 12:41pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama2-70b-inference-api-stuck-on-currently-loading%2F62152%2F3 "2023-11-14T12:41:12Z")

</div>

@prapti19 the service is back 🙂

---

<div class="post-metadata">

**Author:** ![prapti19](https://avatars.discourse-cdn.com/v4/letter/p/9d8465/32.png) [@prapti19](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fprapti19)%5C
**Post date:** [November 14, 2023, 2:22pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama2-70b-inference-api-stuck-on-currently-loading%2F62152%2F4 "2023-11-14T14:22:15Z")

</div>

Thanks for the update @eboraks !

---

<div class="post-metadata">

**Author:** ![CraigJr](https://avatars.discourse-cdn.com/v4/letter/c/43a26b/32.png) [@CraigJr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FCraigJr)%5C
**Post date:** [September 3, 2024, 1:39am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama2-70b-inference-api-stuck-on-currently-loading%2F62152%2F5 "2024-09-03T01:39:46Z")

</div>

I am also having this issue, It has been persisting for at least 4 days. What do you think could be going wrong?