Step 1. Buy a better GPU with at least 6GB VRAM (still very, very slow). 12GB and upwards would be recommended for local LLMs.
Before you do that, you can't really do much unless you have a CPU worth $2k, at least with that amount of RAM.
You can then try Wizard-Vicuna Uncensored or LLaMa.
how do i run the Wizard-Vicuna Uncensored or uncensored LLaMa ? do i install ollama first, and then proceed from there ? details are needed. btw will my system specs will be able to run these ? heres the specs
https://valid.x86.fr/9ud9pc
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.