# Llama 70b model not using GPU

**URL:** <https://discuss.huggingface.co/t/llama-70b-model-not-using-gpu/54780>\
**Category:** Models\
**Created:** [September 13, 2023, 6:18am UTC](https://discuss.huggingface.co/t/llama-70b-model-not-using-gpu/54780 "2023-09-13T06:18:28Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![mac011769](https://avatars.discourse-cdn.com/v4/letter/m/ec9cab/32.png) [@mac011769](https://discuss.huggingface.co/u/mac011769)\
**Post date:** [September 13, 2023, 6:18am UTC](https://discuss.huggingface.co/t/llama-70b-model-not-using-gpu/54780/1 "2023-09-13T06:18:28Z")

</div>

Hello  
I am using Llama2-70b chat model. My PC has Nvidia T1000 GPU with i7-12700 CPU  
When I run my llama model the GPU is not getting used. The output for a simple query like translate to French is taking about 30 mins. The utilization of CPU is 100% where as the GPU usage is 1%. Can somebody help me with this? I have installed CUDA already and have added the paths