# Requirements Llama2

**URL:** <https://discuss.huggingface.co/t/requirements-llama2/81548>\
**Category:** Intermediate\
**Created:** [April 13, 2024, 9:45am UTC](https://discuss.huggingface.co/t/requirements-llama2/81548 "2024-04-13T09:45:06Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![roman174](https://avatars.discourse-cdn.com/v4/letter/r/278dde/32.png) [@roman174](https://discuss.huggingface.co/u/roman174)\
**Post date:** [April 13, 2024, 9:45am UTC](https://discuss.huggingface.co/t/requirements-llama2/81548/1 "2024-04-13T09:45:06Z")

</div>

Hi, can someone please advise me what RAM and GPU requirements the Llama2 model has with 7 billion parameters? If I take the model as it is, without further fine tuning like Lora or quantization. Conversely, what would be the requirements if I used Lora, quantization or both.
