How do I use my 3090 when I also have a 4070 connected?

[mribah78]

I've got a 3090 and a 4070 Super booked up. No matter which PCIE slot I put them in, Tortoise loads my 4070 Super: "Found GPU NVIDIA GeForce RTX 4070 Super". When I try to generate, I get

"Possible latent mismatch: click the "(Re)Compute Voice Latents" button and then try again. Error: CUDA out of memory. Tried to allocate 92.00 MiB. GPU 0 has a total capacty of 11.99 GiB of which 0 bytes is free. Of the allocated memory 7.53 GiB is allocated by PyTorch, and 246.95 MiB is reserved by PyTorch but unallocated."

Is that normal? I can generate fine if I take out the 4070 Super and reboot my PC, but then I can't train DeepFaceLab or run StableDiffusion in the background like I want.