Nvidia 50 Series (Blackwell) support thread: How to get ComfyUI running on your new 50 series GPU.

[comfyanonymous]

I will try keeping this post up to date as much as possible with the latest developments.

To get your nvidia 50 series GPU working with ComfyUI you need a pytorch that has been built against cuda 12.8

In the next few months there will likely be a lot of performance improvements landing in pytorch for these GPUs so I recommend coming back to this page and updating frequently.

Windows

Windows users can download this standalone ComfyUI package with a cuda 12.8 torch build

Manual Install

At this moment Blackwell is not yet supported by stable pytorch or even pytorch nightly.

Torch nightly cu128 is expected to come very soon.

Until it comes to pytorch nightly the easiest way to use it is to use the latest nvidia pytorch docker: https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch

docker run -p 8188:8188 --gpus all -it --rm nvcr.io/nvidia/pytorch:25.01-py3

Inside the docker container:

git clone https://github.com/comfyanonymous/ComfyUI
cd ComfyUI
grep -v 'torchaudio\|torchvision' requirements.txt > temp_requirements.txt
pip install -r temp_requirements.txt
python main.py --listen

[mcmonkey4eva]

There are also Windows prebuilt wheels of pytorch on cuda 128 that nvidia gave w-e-w to publish https://huggingface.co/w-e-w/torch-2.6.0-cu128.nv

[comfyanonymous]

I also had access to those wheels but decided to tell people to use the docker container instead for the manual install since performance is significantly better.

Those wheels are what's in the cu128_50XX standalone package but I'll be switching it out for torch nightly cu128 as soon as that's available.

[mmartial]

FYSA, the nightly for 12.8 appears available https://download.pytorch.org/whl/nightly/cu128

[comfyanonymous]

Yeah I see the package but it's still missing the cu128 torchvision, torchaudio and windows packages.

[mmartial]

It is. Thanks for clarifying the components we are waiting for.

I was trying to follow the guide by removing torchvision and torchaudio
and doing a pip3 install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu128

spandrel too uses torchvision, which forces a downgrade on a Linux installation within a virtualenv.
https://github.com/chaiNNer-org/spandrel/blob/main/libs/spandrel/pyproject.toml#L36

EDIT: I will postpone testing until this is ready. Thanks for the details

[edisonchan]

The Windows version said:
ModuleNotFoundError: No module named 'torchaudio'

[comfyanonymous]

This is because there was no torchaudio cu128 package provided.

The only thing this affects is the audio related nodes so it only affects you if you are using stable audio.

[edisonchan]

nf4 node does not work.

[ltdrdata]

Anything related to NF4 support should be resolved in the node pack repo that provides NF4 feature.