[q1w2]

Great, now how do I run it? Do I need a GPU with over 65GB RAM?

[version_five]

Try this, it's for running llms that won't fit in the gpu: https://github.com/FMInference/FlexGen

[gpm]

Currently that looks like it only supports facebook's opt and galactica models. Though they do appear to plan to add support for more models.

[rnosov]

Generally, you'll need multiply model size by two to get required amount of video RAM. There are 4 sizes, so you might get away with even smaller GPU for say 13B model.

[bioemerl]

Nope, more like 111gb