Pretty sure Llama is all Meta. But tons of people have dropped forks and fine tunes of it since it’s FOSS. This is likely NVIDIA just working off of their base model and applying their RLHF tricks or whatever to make it better. 

 That makes sense. 

 Pardon me sir, but would you happen to have a spare 80gb vram I could borrow? 

 It's open source so I'm assuming this is Nvidia's modified version of the 70b model.

Now I just need 80gb of vram to run it... 

 You really just need 48gb to run a respectable quant. Or 24vram+ram if youre patient 

 Its early days but eventually most PCs etc will be tailored to run models so in 5-10 years the specs on machines will catch up and the models will also become more efficient. 

 Have you seen this: https://youtu.be/GVsUOuSjvcg 

 I'm not patient.  Also I only have 12gb vram + 24gb system ram.  

I wonder what's the cheapest way to get 48gb vram running on a local machine.   

 2 used 3090s would be $1200-1400 and is the current best value. Folks have used p40s but those are ancient and the price actually rose this year 

 But you could run a 48gb model on 2x 24gb cards without issue? 

 Llama is open source model anyone can build on it. Why Zuck said he open sourced it so anyone can do the work and make it better for him.