# Error in loading Llama model

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ferror-in-loading-llama-model%2F152973%3E%5C
**Category:** Models\
**Created:** [April 30, 2025, 7:02am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ferror-in-loading-llama-model%2F152973 "2025-04-30T07:02:25Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Wedyan2023](https://avatars.discourse-cdn.com/v4/letter/w/dec6dc/32.png) [@Wedyan2023](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FWedyan2023)%5C
**Post date:** [April 30, 2025, 7:02am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ferror-in-loading-llama-model%2F152973%2F1 "2025-04-30T07:02:25Z")

</div>

Hi everyone,  
I’ve worked with different versions of LLaMA, and they worked well for me initially. However, over the past two months, they’ve stopped working.  
The error message is:  
An error occurred during generation.

Details: Error code: 403 - {‘error’: ‘The model meta-llama/Meta-Llama-3-8B-Instruct is too large to be loaded automatically (16GB \> 10GB).’}