So according the link below, the "GPU cache memory is a fixed size on NVIDIA cards and is much smaller than the amount of total GPU memory available."

Right now we are using 2080ti cards w 11GB of RAM. Total usage for a project that maxes out the GPU Memory uses about 3GB of the GPU's memory. It seems adding a second GPU doesn't improve the GPU Memory usages (though vmix uses more memory overall between the two).

My question is -- does anyone know if there's a larger cache memory on a 24GB Quadro RTX 5000 or 48GB Quadro RTX 6000? Obviously, they have more overall memory but I don't know if they have the same fixed size with their cache memory.

https://www.vmix.com/kno...n-in-the-vmix-status-bar

Additionally, GPU configuration options (such as ECC memory Other times, it's just useful to make sure all the GPU cards are visible and It is also necessary if you've assigned specific clock speeds or power limits to the GPUs (as those Quadro: 4000, 5000, 6000, 7000, M2070-Q, K-series, M-series.
TellPopeyes