gguf-org/docling-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en"
    ],
    "base_model": [
      "ibm-granite/granite-docling-258M"
    ],
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "gguf-connector"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en"
      ],
      "base_model": [
        "ibm-granite/granite-docling-258M"
      ],
      "pipeline_tag": "image-text-to-text",
      "tags": [
        "gguf-connector"
      ]
    },
    "hero_image_url": "https://raw.githubusercontent.com/calcuis/gguf-pack/master/h3a.png",
    "summary": "## docling-gguf `` ggc n3 `` > >GGUF file(s) available. Select which one to use: > >1. docling-iq4_nl.gguf >3. docling-q6_k.gguf >4. docling-q8_0.gguf > >Enter your choice (1 to 3): _ > !screenshot    docling is a multimodal image-text-to-text model engineered for efficient document conversion; for more details, please refer to the base model from ibm🐥 btw, you are able to customize the output token (more tokens longer wait) with ggc n3   ### **reference**",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\nbase_model:\n- ibm-granite/granite-docling-258M\npipeline_tag: image-text-to-text\ntags:\n- gguf-connector\n---\n## docling-gguf\n- run it with `gguf-connector`; simply execute the command below in console/terminal\n```\nggc n3\n```\n>\n>GGUF file(s) available. Select which one to use:\n>\n>1. docling-iq4_nl.gguf\n>3. docling-q6_k.gguf\n>4. docling-q8_0.gguf\n>\n>Enter your choice (1 to 3): _\n>\n- opt a `gguf` file in your current directory to interact with; nothing else\n\n![screenshot](https://raw.githubusercontent.com/calcuis/gguf-pack/master/n3.png)\n\n<div style=\"display: flex; align-items: center;\">\n    <img src=\"https://raw.githubusercontent.com/calcuis/gguf-pack/master/h3a.png\" alt=\"Granite Docling Logo\" style=\"width: 200px; height: auto; margin-right: 20px;\">\n    <div>\n        <p>docling is a multimodal image-text-to-text model engineered for efficient document conversion; for more details, please refer to the base model from <a href=\"https://huggingface.co/ibm-granite/granite-docling-258M\">ibm</a>🐥 btw, you are able to customize the output token (more tokens longer wait) with ggc n3</p>\n    </div>\n</div>\n\n### **reference**\n- gguf-connector ([pypi](https://pypi.org/project/gguf-connector))",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "gguf-connector",
    "image-text-to-text",
    "en",
    "base_model:ibm-granite/granite-docling-258M",
    "base_model:quantized:ibm-granite/granite-docling-258M",
    "license:apache-2.0",
    "region:us"
  ],
  "likes": 2,
  "downloads": 125,
  "gated": false,
  "private": false,
  "last_modified": "2025-09-22T02:55:48.000Z",
  "created_at": "2025-09-21T21:31:34.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": ""
}

{
  "_id": "68d06eb6ed0555e8b73e3f67",
  "id": "gguf-org/docling-gguf",
  "modelId": "gguf-org/docling-gguf",
  "sha": "2da7846c7fd6086b996ef268f42032a0e4d67641",
  "createdAt": "2025-09-21T21:31:34.000Z",
  "lastModified": "2025-09-22T02:55:48.000Z",
  "author": "gguf-org",
  "downloads": 125,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "",
  "siblings_count": 16
}