AMD GPU run large language model locally – LLaMA and LoRA: Ubuntu step by step tutorial

Thank you for watching! please consider to subscribe. thank you!
Step by step guide on how to run LLaMA or other models using AMD GPU is shown in this video.
0:6 Intro
1:34 Ensure that ROCm is installed. If not, check the tutorial on
7:53 Install Bitsandbytes library
12:34 Download llama model
13:49 Start the webui and testing
17:50 Download lora model
18:58 Start the webui and load LoRA.

πŸ‘‰The discord server invite is There is a llama bot free to use. see this for demo:

If you would like to support me, here is my Kofi link: and Patreon page:
Thank you!

Leave a Reply

Your email address will not be published. Required fields are marked *

© 2024 EVERYTHING CHATGPT - WordPress Theme by WPEnjoy