Not anymore. The new Ampere based Quadros and Teslas just launched with up to 48GB of RAM. A special datacenter version with 80Gb is also already announced:
https://www.nvidia.com/en-us/data-center/a100/
They are really expensive though. But chassis and rackspace also isn't free. If one beefy node with a couple GPUs can replace have a rack of CPU only Nodes the GPUs are totally worth it.
I'm not too familiar with 3D rendering but in other workloads the GPU speedup is so huge that if its possible to offload to the GPU it made sense to do it from a economical perspective.
Hashing and linear algebra kernels get much more speedup on a GPU than a vfx pipeline does. But I am glad to see reports here detailing that the optimization of vfx is progressing.
Desktop GPUs could have 64GB of GDDR right now but the memory bus width to drive those bits optimally (in primary use case of real-time game rendering, not offline) would up the power and heat dissipation requirements beyond what is currently engineered onto a [desktop] PCIE card.
If 8k gaming becomes a real thing you can expect work to be done towards a solution, but until then not so much.
