I see two big constraints to use it right now:<p>- This runs on the CPU only and does not require GPU. It requires around 60GB of CPU memory for Vicuna-13B.<p>also<p>- We release Vicuna weights as delta weights to comply with the LLaMA model license. You can add our delta to the original LLaMA weights to obtain the Vicuna weights. Instructions:<p>...<p>This conversion command needs around 60 GB of CPU RAM.<p>Hope they can optimize it further, to make it work with lesser hardware.