CO

comfy models

ComfyGGUF by usomethingUpdated 2026-07-21
Download on Hugging Face
Parameters12.8B
Context—
Layers—
Architectureqwen_image
Smallest quant8.3 GB
Quick answer

comfy models needs about 9.8 GB of memory at its main file (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU.

comfy models is a 12.8B-parameter Comfy model in GGUF format, quantized by usomething. The repository has 1 quant file, from 8.3 GB to 8.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.3 GB 9.8 GB
Too big Get file →

What GPU do you need for comfy models?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (8.3 GB file, about 9.8 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen_image
Parameters12.8B

Source

Quantized byusomething
FamilyComfy
Licenseapache-2.0
Downloads (HF)11
Last updated2026-07-21

Frequently asked questions about comfy models

How much VRAM does comfy models need?

About 9.8 GB at its main file with an 8K context window. That is the 8.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run comfy models on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of comfy models GGUF?

It depends on the quant: file is 8.3 GB.

Where can I download comfy models GGUF?

The files are on Hugging Face in the usomething/comfy-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does comfy models use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More Comfy models

All Comfy →

Other medium models

All medium models →