# Error in loading Llama model

**URL:** <https://discuss.huggingface.co/t/error-in-loading-llama-model/152973>\
**Category:** Models\
**Created:** [April 30, 2025, 7:02am UTC](https://discuss.huggingface.co/t/error-in-loading-llama-model/152973 "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](https://discuss.huggingface.co/u/Wedyan2023)\
**Post date:** [April 30, 2025, 7:02am UTC](https://discuss.huggingface.co/t/error-in-loading-llama-model/152973/1 "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).’}