Windows Titan RTX issue

I have a Titan RTX with 24GB VRAM, however I keep running into this:

torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 28.86 GiB. GPU 0 has a total capacity of 24.00 GiB of which 3.80 GiB is free. Of the allocated memory 18.56 GiB is allocated by PyTorch, and 395.50 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)

Does this not with with the Titan RTX?

No source file or test is named. Start by reproducing the reported PyTorch CUDA out-of-memory error on a Titan RTX and tracing the FramePack entry point that allocates GPU memory; compare the requested allocation with the model's expected requirements. Done means determining whether the hardware is supported and documenting or fixing the confirmed cause.

Written by the indexing model from the issue text.