Struggling with Local LLMs

Hey guys,

So my senior just discovered Local-LLMs and he is obsessed with setting up a local LLM to answer questions about personal documents sourced from diffrent platforms, DBs, PDFS, URLs etc. His idea is to pitch this to some client. From what I have been able to set up, gpt4all windows version (does not use GPU), GPT4All code version (Also not sure if it can use GPU) and private GPT, The time it takes for the LLM to answer …

artificial client dbs documents etc gpt4all hey llm llms pitch platforms questions set windows