Overview

Qwen Image Edit 2509 GGUF is a specialized image-to-image model optimized for local deployment via the GGUF format. Unlike general-purpose diffusion models, this version is tailored for precise image manipulation and editing tasks, allowing developers to modify visual content based on specific prompts while maintaining structural consistency. By leveraging GGUF quantization, the model significantly lowers the VRAM barrier, making it accessible for integration into edge applications or local workflows without requiring enterprise-grade hardware. It is particularly useful for building automated asset pipelines, AI-driven photo editors, or interactive design tools where low-latency local inference is critical. Compared to cloud-based APIs, it offers full data privacy and eliminates per-call costs under the permissive Apache-2.0 license.

Highlights

Optimized GGUF format for efficient local inference
Precise image-to-image editing and modification capabilities
Low VRAM requirements for accessible edge deployment
Permissive Apache-2.0 license for commercial integration
Reduced latency compared to cloud-based image APIs

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("QuantStack/Qwen-Image-Edit-2509-GGUF")
tokenizer = AutoTokenizer.from_pretrained("QuantStack/Qwen-Image-Edit-2509-GGUF")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download QuantStack/Qwen-Image-Edit-2509-GGUF

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download QuantStack/Qwen-Image-Edit-2509-GGUF config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('QuantStack/Qwen-Image-Edit-2509-GGUF')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/QuantStack/Qwen-Image-Edit-2509-GGUF

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/QuantStack/Qwen-Image-Edit-2509-GGUF

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('QuantStack/Qwen-Image-Edit-2509-GGUF')
tokenizer = AutoTokenizer.from_pretrained('QuantStack/Qwen-Image-Edit-2509-GGUF')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model QuantStack/Qwen-Image-Edit-2509-GGUF

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model QuantStack/Qwen-Image-Edit-2509-GGUF README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('QuantStack/Qwen-Image-Edit-2509-GGUF')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/QuantStack/Qwen-Image-Edit-2509-GGUF.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/QuantStack/Qwen-Image-Edit-2509-GGUF.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'QuantStack/Qwen-Image-Edit-2509-GGUF')

Full Documentation

来源: HuggingFace

---
language:

en

zh

license: apache-2.0
base_model:

Qwen/Qwen-Image-Edit-2509

library_name: gguf
pipeline_tag: image-to-image
---

This GGUF file is a direct conversion of Qwen/Qwen-Image-Edit-2509

Type | Name | Location | Download
| ------------ | -------------------------------------------------- | --------------------------------- | -------------------------
| Main Model | Qwen-Image | ComfyUI/models/unet | GGUF (this repo)
| Main Text Encoder | Qwen2.5-VL-7B | ComfyUI/models/text_encoders | Safetensors / GGUF |
| Text_Encoder (mmproj) | Qwen2.5-VL-7B-Instruct-mmproj-BF16 | ComfyUI/models/text_encoders (same folder as your main text encoder) | GGUF (this repo)
| VAE | Qwen-Image VAE | ComfyUI/models/vae | Safetensors (this repo) |

Since this is a quantized model, all original licensing terms and usage restrictions remain in effect.

Usage

The model can be used with the ComfyUI custom node ComfyUI-GGUF by city96

Update — October 18, 2025

The lower quants Q2_K, Q3_K_M, Q3_K_S, Q4_0, Q4_1, Q4_K_S, and Q4_K_M have been updated, providing improved results.