calcuis/qwen-image-gguf Q3_K_S GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
calcuis/qwen-image-gguf overview
gguf quantized version of qwen-image >GGUF file(s) available. Select which one to use: >1. qwen-image-iq2s.gguf >2. qwen-image-iq4nl.gguf >3. qwen-image-q40.gguf >4. qwen-image-q80.gguf >Enter your choice (1 to 4): _ >
Downloads
1,033
Likes
23
Pipeline
text-to-image
Library
diffusers
Visibility
Public
Access
Open
Repository Files & Downloads
42 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| qwen-image-bf16.gguf | GGUF | BF16 | 38.09 GB | Download |
| qwen-image-distilled-iq3_s.gguf | GGUF | IQ3_S | 8.36 GB | Download |
| qwen-image-distilled-q4_0.gguf | GGUF | — | 10.80 GB | Download |
| qwen-image-distilled-q4_1.gguf | GGUF | — | 11.98 GB | Download |
| qwen-image-distilled-q5_0.gguf | GGUF | — | 13.17 GB | Download |
| qwen-image-distilled-q5_1.gguf | GGUF | — | 14.36 GB | Download |
| qwen-image-distilled-q6_k.gguf | GGUF | Q6_K | 15.69 GB | Download |
| qwen-image-distilled-q8_0.gguf | GGUF | — | 20.29 GB | Download |
| qwen-image-distilled-tq1_0.gguf | GGUF | — | 6.50 GB | Download |
| qwen-image-distilled-tq2_0.gguf | GGUF | — | 6.51 GB | Download |
| qwen-image-f16.gguf | GGUF | F16 | 38.05 GB | Download |
| qwen-image-iq2_s.gguf | GGUF | IQ2_S | 6.55 GB | Download |
| qwen-image-iq3_xxs.gguf | GGUF | IQ3_XXS | 8.36 GB | Download |
| qwen-image-iq4_nl.gguf | GGUF | IQ4_NL | 10.80 GB | Download |
| qwen-image-iq4_xs.gguf | GGUF | IQ4_XS | 10.20 GB | Download |
| qwen-image-lite-iq2_s.gguf | GGUF | IQ2_S | 6.48 GB | Download |
| qwen-image-lite-iq3_s.gguf | GGUF | IQ3_S | 8.33 GB | Download |
| qwen-image-lite-iq3_xxs.gguf | GGUF | IQ3_XXS | 8.33 GB | Download |
| qwen-image-lite-iq4_nl.gguf | GGUF | IQ4_NL | 10.76 GB | Download |
| qwen-image-lite-iq4_xs.gguf | GGUF | IQ4_XS | 10.17 GB | Download |
| qwen-image-lite-mxfp4_moe.gguf | GGUF | — | 20.27 GB | Download |
| qwen-image-lite-q4_0.gguf | GGUF | — | 10.76 GB | Download |
| qwen-image-lite-q5_0.gguf | GGUF | — | 13.14 GB | Download |
| qwen-image-lite-q6_k.gguf | GGUF | Q6_K | 15.66 GB | Download |
| qwen-image-lite-q8_0.gguf | GGUF | — | 20.26 GB | Download |
| qwen-image-lite-tq1_0.gguf | GGUF | — | 6.47 GB | Download |
| qwen-image-lite-tq2_0.gguf | GGUF | — | 6.52 GB | Download |
| qwen-image-q2_k.gguf | GGUF | Q2_K | 6.59 GB | Download |
| qwen-image-q2_k_s.gguf | GGUF | Q2_K_S | 6.47 GB | Download |
| qwen-image-q3_k_l.gguf | GGUF | Q3_K_L | 8.53 GB | Download |
| qwen-image-q3_k_m.gguf | GGUF | Q3_K_M | 8.43 GB | Download |
| qwen-image-q3_k_s.gguf | GGUF | Q3_K_S | 8.36 GB | Download |
| qwen-image-q4_0.gguf | GGUF | — | 10.80 GB | Download |
| qwen-image-q4_1.gguf | GGUF | — | 11.98 GB | Download |
| qwen-image-q4_k_m.gguf | GGUF | Q4_K_M | 10.93 GB | Download |
| qwen-image-q4_k_s.gguf | GGUF | Q4_K_S | 10.80 GB | Download |
| qwen-image-q5_0.gguf | GGUF | — | 13.17 GB | Download |
| qwen-image-q5_1.gguf | GGUF | — | 14.36 GB | Download |
| qwen-image-q5_k_m.gguf | GGUF | Q5_K_M | 13.24 GB | Download |
| qwen-image-q5_k_s.gguf | GGUF | Q5_K_S | 13.17 GB | Download |
| qwen-image-q6_k.gguf | GGUF | Q6_K | 15.69 GB | Download |
| qwen-image-q8_0.gguf | GGUF | — | 20.29 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "apache-2.0",
"language": [
"en"
],
"base_model": [
"Qwen/Qwen-Image"
],
"pipeline_tag": "text-to-image",
"library_name": "diffusers",
"widget": [
{
"text": "cute anime girl with massive fennec ears and a big fluffy fox tail with long wavy blonde hair between eyes and large blue eyes blonde colored eyelashes chubby wearing oversized clothes summer uniform long blue maxi skirt muddy clothes happy sitting on the side of the road in a run down dark gritty cyberpunk city with neon and a crumbling skyscraper in the rain at night while dipping her feet in a river of water she is holding a sign that says \"ComfyUI is the best\" written in cursive",
"output": {
"url": "https://huggingface.co/calcuis/qwen-image-gguf/resolve/main/workflow-demo1.png"
}
},
{
"text": "cute anime girl with massive fennec ears and a big fluffy fox tail with long wavy blonde hair between eyes and large blue eyes blonde colored eyelashes chubby wearing oversized clothes summer uniform long blue maxi skirt muddy clothes happy sitting on the side of the road in a run down dark gritty cyberpunk city with neon and a crumbling skyscraper in the rain at night while dipping her feet in a river of water she is holding a sign that says \"PIG is the best\" written in cursive",
"output": {
"url": "https://huggingface.co/calcuis/qwen-image-gguf/resolve/main/workflow-demo2.png"
}
},
{
"text": "cute anime girl with massive fennec ears and a big fluffy fox tail with long wavy blonde hair between eyes and large blue eyes blonde colored eyelashes chubby wearing oversized clothes summer uniform long blue maxi skirt muddy clothes happy sitting on the side of the road in a run down dark gritty cyberpunk city with neon and a crumbling skyscraper in the rain at night while dipping her feet in a river of water she is holding a sign that says \"1+1=2 is it correct?\" written in cursive",
"output": {
"url": "https://huggingface.co/calcuis/qwen-image-gguf/resolve/main/workflow-demo3.png"
}
}
],
"tags": [
"gguf-node",
"gguf-connector"
],
"frontmatter": {
"license": "apache-2.0",
"language": [
"en"
],
"base_model": [
"Qwen/Qwen-Image"
],
"pipeline_tag": "text-to-image",
"library_name": "diffusers",
"widget": [
"text: >-",
"text: >-",
"text: >-"
],
"tags": [
"gguf-node",
"gguf-connector"
]
},
"hero_image_url": "https://raw.githubusercontent.com/calcuis/comfy/master/qwen-image.png",
"summary": "# **gguf quantized version of qwen-image** `` ggc q5 `` > >GGUF file(s) available. Select which one to use: > >1. qwen-image-iq2_s.gguf >2. qwen-image-iq4_nl.gguf >3. qwen-image-q4_0.gguf >4. qwen-image-q8_0.gguf > >Enter your choice (1 to 4): _ >",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\nbase_model:\n- Qwen/Qwen-Image\npipeline_tag: text-to-image\nlibrary_name: diffusers\nwidget:\n- text: >-\n cute anime girl with massive fennec ears and a big fluffy fox tail with long\n wavy blonde hair between eyes and large blue eyes blonde colored eyelashes\n chubby wearing oversized clothes summer uniform long blue maxi skirt muddy\n clothes happy sitting on the side of the road in a run down dark gritty\n cyberpunk city with neon and a crumbling skyscraper in the rain at night\n while dipping her feet in a river of water she is holding a sign that says\n \"ComfyUI is the best\" written in cursive\n output:\n url: workflow-demo1.png\n- text: >-\n cute anime girl with massive fennec ears and a big fluffy fox tail with long\n wavy blonde hair between eyes and large blue eyes blonde colored eyelashes\n chubby wearing oversized clothes summer uniform long blue maxi skirt muddy\n clothes happy sitting on the side of the road in a run down dark gritty\n cyberpunk city with neon and a crumbling skyscraper in the rain at night\n while dipping her feet in a river of water she is holding a sign that says\n \"PIG is the best\" written in cursive\n output:\n url: workflow-demo2.png\n- text: >-\n cute anime girl with massive fennec ears and a big fluffy fox tail with long\n wavy blonde hair between eyes and large blue eyes blonde colored eyelashes\n chubby wearing oversized clothes summer uniform long blue maxi skirt muddy\n clothes happy sitting on the side of the road in a run down dark gritty\n cyberpunk city with neon and a crumbling skyscraper in the rain at night\n while dipping her feet in a river of water she is holding a sign that says\n \"1+1=2 is it correct?\" written in cursive\n output:\n url: workflow-demo3.png\ntags:\n- gguf-node\n- gguf-connector\n---\n# **gguf quantized version of qwen-image**\n- run it straight with `gguf-connector`\n```\nggc q5\n```\n>\n>GGUF file(s) available. Select which one to use:\n>\n>1. qwen-image-iq2_s.gguf\n>2. qwen-image-iq4_nl.gguf\n>3. qwen-image-q4_0.gguf\n>4. qwen-image-q8_0.gguf\n>\n>Enter your choice (1 to 4): _\n>\n## **run it with gguf-node via comfyui**\n- drag **qwen-image** to > `./ComfyUI/models/diffusion_models`\n- drag **qwen2.5-vl-7b** [[4.43GB](https://huggingface.co/chatpig/qwen2.5-vl-7b-it-gguf/blob/main/qwen2.5-vl-7b-it-q4_0.gguf)] to > `./ComfyUI/models/text_encoders`\n- drag **pig** [[254MB](https://huggingface.co/calcuis/pig-vae/blob/main/pig_qwen_image_vae_fp32-f16.gguf)] to > `./ComfyUI/models/vae`\n\n<Gallery />\n\n\n\ntip: the text encoder used for this model is qwen2.5-vl-**7b**; get more encoder either [here](https://huggingface.co/calcuis/pig-encoder/tree/main) (pig quant) or [here](https://huggingface.co/chatpig/qwen2.5-vl-7b-it-gguf/tree/main) (llama.cpp quant); the size is different from the one (qwen2.5-vl-**3b**) used in **omnigen2**\n\n## **run it with diffusers**\n```py\nimport torch\nfrom diffusers import DiffusionPipeline, GGUFQuantizationConfig, QwenImageTransformer2DModel\n\nmodel_path = \"https://huggingface.co/calcuis/qwen-image-gguf/blob/main/qwen-image-q2_k.gguf\"\ntransformer = QwenImageTransformer2DModel.from_single_file(\n model_path,\n quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),\n torch_dtype=torch.bfloat16,\n config=\"callgg/qi-decoder\",\n subfolder=\"transformer\"\n)\npipe = DiffusionPipeline.from_pretrained(\n \"callgg/qi-decoder\",\n transformer=transformer,\n torch_dtype=torch.bfloat16,\n)\npipe.enable_model_cpu_offload()\n\nprompt = \"a pig holding a sign that says hello world\"\npositive_magic = {\"en\": \"Ultra HD, 4K, cinematic composition.\"}\nnegative_prompt = \" \"\nimage = pipe(\n prompt=prompt + positive_magic[\"en\"],\n negative_prompt=negative_prompt,\n height=1024,\n width=1024,\n num_inference_steps=24,\n true_cfg_scale=2.5,\n generator=torch.Generator()\n).images[0]\nimage.save(\"output.png\")\n```\n\nnote: diffusers not yet supported t and i quants; opt gguf-node via comfyui or run it straight with gguf-connector\n\n### **reference**\n- base model from [qwen](https://huggingface.co/Qwen)\n- distilled model from [modelscope](https://github.com/modelscope/DiffSynth-Studio)\n- lite model is a lora merge from [lightx2v](https://huggingface.co/lightx2v/Qwen-Image-Lightning)\n- comfyui from [comfyanonymous](https://github.com/comfyanonymous/ComfyUI)\n- diffusers from [huggingface](https://github.com/huggingface/diffusers)\n- gguf-node ([pypi](https://pypi.org/project/gguf-node)|[repo](https://github.com/calcuis/gguf)|[pack](https://github.com/calcuis/gguf/releases))\n- gguf-connector ([pypi](https://pypi.org/project/gguf-connector))",
"related_quantizations": []
},
"tags": [
"diffusers",
"gguf",
"gguf-node",
"gguf-connector",
"text-to-image",
"en",
"base_model:Qwen/Qwen-Image",
"base_model:quantized:Qwen/Qwen-Image",
"license:apache-2.0",
"region:us"
],
"likes": 23,
"downloads": 1033,
"gated": false,
"private": false,
"last_modified": "2025-08-14T09:52:33.000Z",
"created_at": "2025-08-05T12:10:41.000Z",
"pipeline_tag": "text-to-image",
"library_name": "diffusers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6891f4c1d9af3df8873e2e2a",
"id": "calcuis/qwen-image-gguf",
"modelId": "calcuis/qwen-image-gguf",
"sha": "5317d72639a93207af4241a0d14ecc576fa6b98f",
"createdAt": "2025-08-05T12:10:41.000Z",
"lastModified": "2025-08-14T09:52:33.000Z",
"author": "calcuis",
"downloads": 1033,
"likes": 23,
"gated": false,
"private": false,
"pipeline_tag": "text-to-image",
"library_name": "diffusers",
"siblings_count": 48
}