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

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

The recommended download is the standalone package with nightly pytorch 2.7 cu128 that you can [download from here](https://github.com/comfyanonymous/ComfyUI/releases/download/latest/ComfyUI_windows_portable_nvidia_or_cpu_nightly_pytorch.7z)

Old package with torch 2.6

Windows users can download [this standalone ComfyUI package with a cuda 12.8 torch build](https://github.com/comfyanonymous/ComfyUI/releases/download/latest/ComfyUI_cu128_50XX.7z)

### Manual Install

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

pytorch nightly cu128 is available for Windows and Linux:

```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128```

You can also use the Nvidia Pytorch Docker Container as an alternative which might give more performance.

Link: https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch

Here's how to use it:

`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
```

_Originally posted by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/discussions/6643_