Yes, but the use cases for them require the support for them specifically. They also require a forced air cooling solution to run in a desktop. I had a handful of Tesla T4 cards but sold them as they werent as useful as I had hoped for in widows, I think linux has better support.
For the money a used quadro P series, or Quadro RTX works well. A p5000 is great with its 16gb of VRAM.
Thanks a lot. Actually from this video I concluded there is a difference between those cards - not only they are factory overclocked, but they also have slightly different dies. I.e., this is not a manufacturer's overlooking, this is actually Nvidia's selection. I assume what happens is that Nvidia tests their chips and then marks them according to the frequency it can hold. Here is more about it - https://www.thenerdmag.com/difference-between-nvidia-tu102-300-vs-tu102-300a-turing-a-and-non-a-gpu-variants/
I need two cards for a machine learning rig and I need to ensure they are stable and do not overheat. So I will probably go for a pricier model.
Speaking about the brand. Unfortunately EVGA is not available in my region, but I can choose between MSI, ZOTAC, GIGABYTE, ASUS, and some other lesser known brands. I think that MSI GEFORCE RTX 2080 TI SEA HAWK X would be a good choice. It's manufacturer's specified boost frequency is the highest - 1755 MHz.