comfyanonymous/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-01-26 19:19:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated Which GPU should I buy for ComfyUI (markdown)

comfyanonymous
2025-10-17 18:06:22 -04:00
parent a6eb97a72d
commit f071c1a146
1 changed files with 7 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
Which-GPU-should-I-buy-for-ComfyUI.md

@@ -43,21 +43,19 @@ Anything older than 2000 series like Volta or Pascal should be avoided because t
Officially supported in pytorch.
Works well if the card is [officially supported](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html) by ROCm but they are slow compared to price equivalent Nvidia GPUs mainly because of the lack of an optimized implementation of [torch.nn.functional.scaled_dot_product_attention](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html) for consumer GPUs.
Works well if the card is [officially supported](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html) by ROCm but can be a bit slow compared to price equivalent Nvidia GPUs depending on the GPU. The later the GPU generation the better things work.
RDNA 4, MI300X: Confirmed "A tier" experience on latest ComfyUI and latest pytorch nightly.
Unsupported cards might be a real pain to get running.
# C Tier
## AMD (Windows)
Official pytorch version that works but can be a bit slow compared to the Linux builds. Oldest officialy supported generation is the 7000 series.
## Intel (Linux + Windows)
Officially supported in pytorch. People seem to get it working fine but I had trouble with my integrated intel GPU.
## AMD (Windows)
Unofficial pytorch rocm builds for windows have come out that work decently but they are still a bit of a pain to get working properly.
Things might improve in the future once they have official pytorch ROCm working on windows.
Officially supported in pytorch. People seem to get it working fine.
# D Tier