Qwen-Image-2.1 can now run locally on 12GB VRAM with Unsloth GGUFs! The 7B model performs on par with Nano Banana 2.0. For higher quality, you can also run Dynamic FP8 on just 6GB of VRAM via offloading. GGUF: https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF… Guide: https://unsloth.ai/docs/models/qwen-image-2.1…

unsloth/Qwen-Image-2.1-GGUF · Hugging Face

Source: https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#read-our-how-to-run-qwen-image-21-guide-%F0%9F%92%9CRead our How toRun Qwen-Image-2.1 Guide!💜

This is a GGUF quantized version ofQwen-Image-2.1. unsloth/Qwen-Image-2.1-GGUF usesUnsloth Dynamic 2.0methodology for SOTA performance.

sd-cli --diffusion-model qwen-image-2.1-Q4_K_M.gguf \
  --vae qwen_image_2.1_vae_bf16.safetensors \
  --llm Qwen3-VL-8B-Instruct-UD-Q4_K_XL.gguf \
  -p "a cartoon sloth mascot waving, flat vector illustration, bright colours" \
  --steps 20 --cfg-scale 6.0 --sampling-method euler -W 1024 -H 1024 --diffusion-fa \
  -o out.png

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#samplesSamples

Rendered with the Q4_K_M denoiser and the Q4_K_M text encoder, 1024x1024, 20 steps, cfg 6.0, euler.

🤖ModelScope| 🤗HuggingFace| 📑Blog| 🖥️Demo| 🫨Discord| 💬WeChat

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#introductionIntroduction

We are excited to open-sourceQwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just7B parameters in its visual generation component(32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.

Four key improvements define this release:

• Compact and Efficient: a lightweight architecture with mixed-granularity attention and prefix KV cache reuse delivers strong image quality at low computational cost.
• Native Transparency, Unified Creation and Editing: generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photographs, all in one model.
• Versatile Editing: support up to10 reference images, specify local edits via circles, painted annotations, or separate masks, and preserve identity for people and products.
• Realistic Textures and Refined Aesthetics: improved typography, portrait lighting, and fine details for more visually compelling results.

For more details, see theGitHub repoandBlog.

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#quick-startQuick Start

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#installationInstallation

pip install torch>=2.4.0
pip install transformers>=5.17
pip install git+https://github.com/huggingface/diffusers
pip install accelerate pillow

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#text-to-imageText-to-Image

import torch
from diffusers import QwenImage21Pipeline

pipe = QwenImage21Pipeline.from_pretrained(
    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
).to("cuda")

image = pipe(
    prompt="A neon shop sign that reads \"QWEN IMAGE 2.1\", rainy night, reflections on wet pavement",
    width=2048, height=2048,
    num_inference_steps=40,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]

image.save("t2i_example.png")

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#image-editingImage Editing

import torch
from PIL import Image
from diffusers import QwenImage21Pipeline

pipe = QwenImage21Pipeline.from_pretrained(
    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
).to("cuda")

input_image = Image.open("input.png")

image = pipe(
    prompt="Change the background to a sunset beach",
    image=input_image,
    num_inference_steps=40,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]

image.save("edit_example.png")

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#transparent-image-generation-rgbaTransparent Image Generation (RGBA)

Use the recommended prompt format for transparent images:

image = pipe(
    prompt="This is an RGBA image with transparency. A cute cartoon dragon sticker. The image has alpha channel and the background is transparent.",
    width=2048, height=2048,
    num_inference_steps=40,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]

image.save("transparent_example.png")

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#supported-aspect-ratiosSupported Aspect Ratios

aspect_ratios = {
    "1:1":  (2048, 2048),
    "4:3":  (2400, 1792),
    "3:4":  (1792, 2400),
    "3:2":  (2528, 1696),
    "2:3":  (1696, 2528),
    "16:9": (2752, 1536),
    "9:16": (1536, 2752),
}

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#memory-optimizationMemory Optimization

pipe = QwenImage21Pipeline.from_pretrained(
    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
)
pipe.enable_model_cpu_offload()

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#showcaseShowcase

Native transparent image generation

Group photograph generated from six portrait references

Text rendering

https://huggingface.co/unsloth/Qwen-Image-2.1-GGUF#licenseLicense

This model is licensed under theQwen Research License Agreement.

Qwen (@Alibaba_Qwen): Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨

A unified model for both generation and editing, delivering top-tier quality in a lightweight package.

Highlights: 👀

• Compact & exceptionally fast: