If you just want to play with this a bit, around 250$/month should give you enough metal when renting from cheap VDS/dedicated server providers.
I'd love to see a llama model that fits now economically inside 16GB. The 8b is a bit too small when quantised even to 8 bits. A 16-20b model would be perfect.
But I think for 400b models to be viable, the hardware pricing really needs to catch up.
Agreed, it's a lot of money and definitely more than I'd be willing to spend. However, compared to running such 400b models on a GPU cluster it's extremely cheap (and much slower)