Qwen-Image-2.1-GGUF

Abiray/Qwen-Image-2.1-GGUF

Qwen-Image-2.1-GGUF is a text-to-image model from Abiray. Use it when you need an image from a text prompt. The card lists the license as other.

This repository provides quantized GGUF checkpoints for Qwen/Qwen-Image-2.1, optimized for low-VRAM inference in ComfyUI using the ComfyUI-GGUF custom node.

Downloads · 30 days

22.9K

19% of all-time downloads

All-time downloads

118K

Public

Repo size

29.9 GB

Likes

116

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf29.9 GB · 100%

At a glance

Task: Text-to-Image
License: other
Access: Public
Created: Sep 20, 2026
Updated: Sep 20, 2026
SHA: c9dd1210

Try a prompt

Base models

Qwen/Qwen-Image-2.1

Model card

From the Hugging Face model README

Qwen-Image-2.1 GGUF Quants

This repository provides quantized GGUF checkpoints for Qwen/Qwen-Image-2.1, optimized for low-VRAM inference in ComfyUI using the ComfyUI-GGUF custom node.

Quantizing the diffusion transformer drastically reduces memory pressure during generation while preserving sharp detail, composition, and prompt alignment.

📦 Quantization Breakdown & File Details

Filename	Quant Type	Size	Recommended VRAM / Profile
`qwen_image_2.1_Q8_0.gguf`	Q8_0	7.59 GB	12 GB+ (Near-lossless fidelity)
`qwen_image_2.1_Q6_K.gguf`	Q6_K	5.88 GB	10–12 GB (High quality sweet spot)
`qwen_image_2.1_Q5_K_M.gguf`	Q5_K_M	5.01 GB	8–10 GB (Balanced performance & memory)
`qwen_image_2.1_Q4_K_M.gguf`	Q4_K_M	4.19 GB	6–8 GB (Standard consumer GPU baseline)
`qwen_image_2.1_Q4_K_S.gguf`	Q4_K_S	4.06 GB	6–8 GB (Compact 4-bit)
`qwen_image_2.1_Q3_K_M.gguf`	Q3_K_M	3.19 GB	4–6 GB (Extreme budget / minimum VRAM)

🖼️ Sample Generations (Q4_K_M)

🧩 Required Components (Text Encoders & VAE)

To run these models in ComfyUI, you will need the matching text encoders and VAE:

Text Encoders:
- Download from: Comfy-Org/Qwen-Image-2.1 Text Encoders
- Place files into: ComfyUI/models/clip/ (or ComfyUI/models/text_encoders/)
VAE:
- Download from: Comfy-Org/Qwen-Image-2.1 VAE
- Place files into: ComfyUI/models/vae/
Diffusion Model (This Repo):
- Download your preferred .gguf file from above.
- Place into: ComfyUI/models/diffusion_models/ (or ComfyUI/models/unet/)

🎨 Included Ready-to-Use Workflows

Both Text-to-Image and Image-to-Image editing workflows are packaged in this repo:

Text-to-Image: Qwen_Image_2.1_GGUF_Text2Image.json
Image-to-Image / Editing: Qwen_Image_2.1_GGUF_Image2Image_Edit.json

How to Use:

Ensure you have installed ComfyUI-GGUF (search for ComfyUI-GGUF inside the ComfyUI Manager).
Drag and drop either of the .json workflow files into your ComfyUI workspace.
In the Unet Loader (GGUF) node, select the downloaded .gguf file.
Verify your CLIP/Text Encoder and VAE node loaders point to the files downloaded above.
Queue prompt and generate!

👏 Acknowledgments & Credits

Base model developed by the Qwen Team / Alibaba Cloud: Qwen/Qwen-Image-2.1.
ComfyUI integration assets and pipeline weights provided by Comfy-Org.
GGUF quantization powered by llama.cpp and ComfyUI-GGUF.

Task: Text-to-Image
License: other
Created: Sep 20, 2026
Updated: Sep 20, 2026