Quoted from the releases 3.1.10 thread >>
XTX stats are excellent for the price, but are closer to (but better than) the RTX 3060 TI actually, which is of course well under half the XTX price and around 25% of the 4090 price. At SD resolutions, my benchmarks for the 3060 TI are mostly faster than the XTX. I’m now off to find some SD benchmarks posted for the 4090
The odd thing is that there are wild variations between some of the models’ performances - my 3060 TI performs badly on Gaia and one or two others, but mostly very well.
Topaz Video AI v3.1.10
System Information
OS: Windows v10.2009
CPU: AMD Ryzen 7 5800X 8-Core Processor 31.948 GB
GPU: NVIDIA GeForce RTX 3060 Ti 7.8496 GB
Processing Settings: device: -2 vram: 0.99 instances: 1
Input Resolution: 1920x1080
Benchmark Results
Artemis 1X: 10.73 fps 2X: 5.73 fps 4X: 1.56 fps
Proteus 1X: 9.21 fps 2X: 5.2 fps 4X: 1.53 fps
Gaia 1X: 4.05 fps 2X: 2.48 fps 4X: 1.65 fps
4X Slowmo Apollo: 12.23 fps Chronos: 8.61 fps Chronos Fast: 11.08 fps
Topaz Video AI v3.1.10
System Information
OS: Windows v10.2009
CPU: AMD Ryzen 7 5800X 8-Core Processor 31.948 GB
GPU: NVIDIA GeForce RTX 3060 Ti 7.8496 GB
Processing Settings: device: -2 vram: 0.99 instances: 1
Input Resolution: 640x480
Benchmark Results
Artemis 1X: 60.73 fps 2X: 28.07 fps 4X: 9.02 fps
Proteus 1X: 53.79 fps 2X: 25.98 fps 4X: 8.69 fps
Gaia 1X: 23.7 fps 2X: 15.88 fps 4X: 9.99 fps
4X Slowmo Apollo: 72.99 fps Chronos: 45.99 fps Chronos Fast: 59.19 fps
The law of diminishing returns certainly applies here for me, because I use Artemis or Proteus for 2x upscales and Apollo or Chronos Fast for slomo. And if I upgrade the GPU in my existing no. 2 PC to a 3060 TI (making 2 systems with 3060 TI), I can get more throughput at 1080p or below than a single 4090, for 25% of the price of a single 4090 upgrade.
These benchmark tables are a brilliant help in choosing what to do! 
