Run LLMs without GPUs | local-llm

[@OsamaAltobuli]

Thanks for sharing this. What the performance compared to the GPU based machines?

[@EduardoRodriguezRocks]

is not this the deault behaviour when using llamacpp

[@armanshirzad4409]

great thanks! so question can i use this to run a downloaded llm , instead of accessing hugging face ?

[@rakeshreddy2791]

hey rishab great video.. can we fine tune the model using local-llm??

[@Heet10]

Hello Sir, Thank you for reading my message Sir, I just finished my UG(BSc.IT) and I'm interested in the Cloud Computing Field as a fresher should I start preparing for DevOps or Cloud engineering to land a Job in Cloud Computing as soon as possible, And any advice that you would help me in career growth wise.

[@rishabhjain5100]

It’s only for the inferencing ??

[@armantech5926]

Yes, I also thought that is not real local LLM. It's inference.

[@bradkeane1246]

can you talk to the models in english and have them answer you? you did not even demonstrate this?