ComfyUI Node: FP8 / MXFP8 Model Patch (SM89+)

Authored by marduk191

Created

Updated

0 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

optimization

Inputs

model MODEL
mode
  • fp8
  • mxfp8
accumulator
  • fp16
  • fp32

Outputs

MODEL

Extension: ComfyUI-fp8_cublas

ComfyUI custom node that patches loaded models (Flux, SDXL, etc.) to run Linear layers in FP8 or MXFP8, unlocking tensor-core throughput on Ada Lovelace (RTX 4090) and Blackwell (RTX 5090) GPUs.

Authored by marduk191

Looking for a different node?

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more