Comfy-Org · 2026-08-03 · notable
MiniMax H3 Day-0 Support in ComfyUI — 2K video generation on an RTX 3060
Comfy-Org shipped native ComfyUI support for MiniMax H3 on launch day, with pruned and quantized weights that cut memory from 123.6 GB to 42.5 GB so the open video model runs on a consumer RTX 3060.
Day-0 ComfyUI workflows plus a pruned + quantized H3 that fits on an RTX 3060.
What is it?
Comfy-Org's Day-0 integration for MiniMax H3 lands native workflow templates for text-to-video, image-to-video, first-and-last-frame control, and reference-to-video, all inside ComfyUI. The release ships alongside a pruned and quantized model repo on Hugging Face so the omni-modal H3 stack works out of the box in local Comfy graphs.
How does it work?
The Comfy build applies pruning and quantization that shrink H3's memory footprint from 123.6 GB in full precision down to 42.5 GB, a 66% reduction. Dynamic VRAM offloading then lets consumer GPUs like the RTX 3060 run the model by paging weights between GPU memory and system RAM during each generation step.
Why does it matter?
H3 generates up to 15-second clips at 2K resolution with native stereo audio, and the ComfyUI path removes the two biggest blockers to local use: workflow plumbing and VRAM. Creators who already live in Comfy can drop in the templates and generate video plus audio on hardware they own, without paying for a hosted API.
Who is it for?
ComfyUI users and local video-generation creators
Try it
huggingface.co/Comfy-Org/MiniMax-H3