city96/flux.2-dev-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "black-forest-labs/FLUX.2-dev",
    "library_name": "gguf",
    "quantized_by": "city96",
    "license": "other",
    "license_name": "flux-dev-non-commercial-license",
    "license_link": "LICENSE.md",
    "tags": [
      "image-generation",
      "image-editing",
      "flux",
      "diffusion-single-file"
    ],
    "pipeline_tag": "image-to-image",
    "frontmatter": {
      "base_model": "black-forest-labs/FLUX.2-dev",
      "library_name": "gguf",
      "quantized_by": "city96",
      "license": "other",
      "license_name": "flux-dev-non-commercial-license",
      "license_link": "LICENSE.md",
      "tags": [
        "image-generation",
        "image-editing",
        "flux",
        "diffusion-single-file"
      ],
      "pipeline_tag": "image-to-image"
    },
    "hero_image_url": "media/flux2dev-image.jpg",
    "summary": "This is a direct GGUF conversion of black-forest-labs/FLUX.2-dev. The model files can be used in ComfyUI with the ComfyUI-GGUF custom node. Place the required model(s) in the following folders: | Type         | Name                                | Location                          | Download         | | ------------ | ----------------------------------- | --------------------------------- | ---------------- | | Main Model   | flux2-dev                           | ComfyUI/models/diffusion_models | GGUF (this repo) | | Text Encoder | Mistral-Small-3.2-24B-Instruct-2506 | ComfyUI/models/text_encoders    | Safetensors / GGUF | | VAE          | flux2 VAE                           | ComfyUI/models/vae              | Safetensors | **Example outputs** - sample size of 1, not strictly representative !sample ### Notes > [!NOTE] > As with Qwen-Image, Q5_K_M, Q4_K_M, Q3_K_M, Q3_K_S and Q2_K have some extra logic as to which blocks to keep in high precision. > > The logic is partially based on guesswork, trial & error, and the graph found in the readme for Freepik/flux.1-lite-8B (which in turn quotes this blog by Ostris) *As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.*",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: black-forest-labs/FLUX.2-dev\nlibrary_name: gguf\nquantized_by: city96\nlicense: other\nlicense_name: flux-dev-non-commercial-license\nlicense_link: LICENSE.md\ntags:\n- image-generation\n- image-editing\n- flux\n- diffusion-single-file\npipeline_tag: image-to-image\n---\n\nThis is a direct GGUF conversion of [black-forest-labs/FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev).\n\nThe model files can be used in [ComfyUI](https://github.com/comfyanonymous/ComfyUI/) with the [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node. Place the required model(s) in the following folders:\n\n| Type         | Name                                | Location                          | Download         |\n| ------------ | ----------------------------------- | --------------------------------- | ---------------- |\n| Main Model   | flux2-dev                           | `ComfyUI/models/diffusion_models` | GGUF (this repo) |\n| Text Encoder | Mistral-Small-3.2-24B-Instruct-2506 | `ComfyUI/models/text_encoders`    | [Safetensors](https://huggingface.co/Comfy-Org/flux2-dev/tree/main/split_files/text_encoders) / [GGUF](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/tree/main) |\n| VAE          | flux2 VAE                           | `ComfyUI/models/vae`              | [Safetensors](https://huggingface.co/Comfy-Org/flux2-dev/blob/main/split_files/vae/flux2-vae.safetensors) |\n\n[**Example outputs**](media/flux2dev-image.jpg) - sample size of 1, not strictly representative\n\n![sample](media/flux2dev-image.jpg)\n\n### Notes\n\n> [!NOTE]\n> As with Qwen-Image, Q5_K_M, Q4_K_M, Q3_K_M, Q3_K_S and Q2_K have some extra logic as to which blocks to keep in high precision.\n> \n> The logic is partially based on guesswork, trial & error, and the graph found in the readme for [Freepik/flux.1-lite-8B](https://huggingface.co/Freepik/flux.1-lite-8B#motivation) (which in turn quotes [this blog by Ostris](https://ostris.com/2024/09/07/skipping-flux-1-dev-blocks/))\n\n*As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.*\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "image-generation",
    "image-editing",
    "flux",
    "diffusion-single-file",
    "image-to-image",
    "base_model:black-forest-labs/FLUX.2-dev",
    "base_model:quantized:black-forest-labs/FLUX.2-dev",
    "license:other",
    "region:us"
  ],
  "likes": 132,
  "downloads": 19567,
  "gated": false,
  "private": false,
  "last_modified": "2025-11-29T21:34:06.000Z",
  "created_at": "2025-11-25T22:24:44.000Z",
  "pipeline_tag": "image-to-image",
  "library_name": "gguf"
}

{
  "_id": "69262cace0013afb1d03c964",
  "id": "city96/FLUX.2-dev-gguf",
  "modelId": "city96/FLUX.2-dev-gguf",
  "sha": "ade5d688ddab0d9cf4a5b01bf4321e01c115020d",
  "createdAt": "2025-11-25T22:24:44.000Z",
  "lastModified": "2025-11-29T21:34:06.000Z",
  "author": "city96",
  "downloads": 19567,
  "likes": 132,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-to-image",
  "library_name": "gguf",
  "siblings_count": 18
}