Who makes Qwen Image 2.1 GGUF?

Qwen Image 2.1 GGUF is made by Abiray.

Does Qwen Image 2.1 GGUF work in the EU?

Available in the EU. Weights are freely downloadable from Hugging Face and the license shown (qwen-research, "other") has no stated EU exclusion in the provided text; runs locally. Last verified 14 Nov 2026.

How much does Qwen Image 2.1 GGUF cost?

Open source. Free to download from Hugging Face; subject to the qwen-research license terms. Licence: Qwen Research License (other).

Where was Qwen Image 2.1 GGUF shown?

In 1 creator video by AI Search. Most recently by AI Search on 22 Sept 2026, at 15:38 in "Finally! New best local AI image editor is here".

Qwen Image 2.1 GGUF

by Abiray

Try it Hugging Face

Community GGUF quantizations of Qwen-Image-2.1 for low-VRAM text-to-image and image editing in ComfyUI.

Available in EUPlatforms & Infra Image GenerationModel

Updated 14 Nov 2026EU status checked 14 Nov 2026Last shown 22 Sept 2026

Qwen Image 2.1 GGUF at a glance

What is Qwen Image 2.1 GGUF?: Qwen Image 2.1 GGUF is a model from Abiray. Community GGUF quantizations of Qwen-Image-2.1 for low-VRAM text-to-image and image editing in ComfyUI.
Who makes Qwen Image 2.1 GGUF?: Qwen Image 2.1 GGUF is made by Abiray.
Does Qwen Image 2.1 GGUF work in the EU?: Available in the EU. Weights are freely downloadable from Hugging Face and the license shown (qwen-research, "other") has no stated EU exclusion in the provided text; runs locally. Last verified 14 Nov 2026.
How much does Qwen Image 2.1 GGUF cost?: Open source. Free to download from Hugging Face; subject to the qwen-research license terms. Licence: Qwen Research License (other).
Where was Qwen Image 2.1 GGUF shown?: In 1 creator video by AI Search. Most recently by AI Search on 22 Sept 2026, at 15:38 in “Finally! New best local AI image editor is here”.

Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.

About

Qwen-Image-2.1 GGUF is a community repository by Abiray that provides quantized GGUF checkpoints of the diffusion transformer from Alibaba's Qwen/Qwen-Image-2.1. The quantization was made with llama.cpp tooling and is meant to be loaded in ComfyUI through the ComfyUI-GGUF custom node, reducing memory use so the model can run on consumer GPUs.

Six quantization levels are offered, from Q8_0 (7.59 GB, recommended for 12 GB+ VRAM) down to Q3_K_M (3.19 GB, listed for 4–6 GB VRAM). The repo also bundles ready-made ComfyUI workflows for text-to-image and image-to-image editing. A YouTube reviewer testing the Q3 version reported quality similar to the full model, though this is an anecdotal impression.

Users must separately download the matching text encoders and VAE from Comfy-Org/Qwen-Image-2.1 and place them in the usual ComfyUI folders. The files are licensed under the "qwen-research" terms linked to the base model (license: other), so usage restrictions of the upstream license apply.

Key features

Six GGUF quants: Q8_0, Q6_K, Q5_K_M, Q4_K_M, Q4_K_S, Q3_K_M
File sizes from 3.19 GB to 7.59 GB
Runs via the ComfyUI-GGUF Unet Loader node
Includes text-to-image and image-to-image editing ComfyUI workflows
Targets GPUs with roughly 4–12 GB VRAM

1 moment

As seen on YouTube

Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.

AI Search22 Sept 2026

Live demo

Finally! New best local AI image editor is here

Community GGUF quantized versions of Qwen Image 2.1, the smallest at 3.19 GB, for GPUs with about 4 GB VRAM. Creator tests the Q3 version through the GGUF loader node and finds quality similar to the full model.

15:38Open on YouTube