Hmmm weird. I have a 4090 / Ryzen 5800X3D and 64GB and it runs really well. Admittedly it's the 8B model because the intermediate sizes aren't out yet and 70B simply won't fly on a single GPU.
But it really screams. Much faster than I can read. PS: Ollama is just llama.cpp under the hood.
Edit: Ah, wait, I know what's going wrong here. The 22B parameter model is probably too big for your VRAM. Then it gets extremely slow yes.