Single GPU vs multiple GPUs stack (parallel)

[fdm-git]

Hi there and first of all thanks for this great tool!

I was wondering if you could provide any feedback about having a single (eg.) RTX 4090 24GB vs (eg.) 4x 4060ti 16GB.

At the end 4x 4060ti stack tensor and cuda cores count will match a single 4090 tensor and cuda cores, the plus is having the 4x4060ti 16GB stack with a total 64GB of RAM instead of 24GB.

Can't tell if the 4x 4060ti stack memory bandwidth will be a bottleneck compared to a single 4090.

Any feedback will be appreciated, thanks!