I am using a workflow that uses Chronos and GAIA and while my GPU (4090) is maxed out, my CPU (13900K) is only at around 40% utilization.
It is my understanding that topaz doesn’t support multiple gpus. I wonder if you could successfully run two instances of it (if possible) configured for one job each, with each instance mapped to a distinct GPU. If you had a CPU fast enough to keep up that might be interesting. 
edit:
it looks like it sort of works.
ref: Multiple gpu in video ai - Topaz Video AI / General - Topaz Community (topazlabs.com)
