mradermacher/qwen2.5-vl-72b-instruct-heretic-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "coder3101/Qwen2.5-VL-72B-Instruct-heretic",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct/blob/main/LICENSE",
    "license_name": "qwen",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "multimodal",
      "heretic",
      "uncensored",
      "decensored",
      "abliterated"
    ],
    "frontmatter": {
      "base_model": "coder3101/Qwen2.5-VL-72B-Instruct-heretic",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "other",
      "license_link": "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct/blob/main/LICENSE",
      "license_name": "qwen",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "multimodal",
        "heretic",
        "uncensored",
        "decensored",
        "abliterated"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/coder3101/Qwen2.5-VL-72B-Instruct-heretic  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-GGUF **This is a vision model - mmproj files (if any) will be in the static repository.**",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: coder3101/Qwen2.5-VL-72B-Instruct-heretic\nlanguage:\n- en\nlibrary_name: transformers\nlicense: other\nlicense_link: https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct/blob/main/LICENSE\nlicense_name: qwen\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- multimodal\n- heretic\n- uncensored\n- decensored\n- abliterated\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags: nicoboss -->\n<!-- ### quants:  Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->\n<!-- ### quants_skip:  -->\n<!-- ### skip_mmproj:  -->\nweighted/imatrix quants of https://huggingface.co/coder3101/Qwen2.5-VL-72B-Instruct-heretic\n\n<!-- provided-files -->\n\n***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-GGUF\n\n**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-GGUF).**\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ1_S.gguf) | i1-IQ1_S | 22.8 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ1_M.gguf) | i1-IQ1_M | 23.8 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 25.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ2_XS.gguf) | i1-IQ2_XS | 27.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ2_S.gguf) | i1-IQ2_S | 28.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ2_M.gguf) | i1-IQ2_M | 29.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q2_K_S.gguf) | i1-Q2_K_S | 29.7 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q2_K.gguf) | i1-Q2_K | 29.9 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 31.9 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ3_XS.gguf) | i1-IQ3_XS | 32.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ3_S.gguf) | i1-IQ3_S | 34.6 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q3_K_S.gguf) | i1-Q3_K_S | 34.6 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ3_M.gguf) | i1-IQ3_M | 35.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q3_K_M.gguf) | i1-Q3_K_M | 37.8 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q3_K_L.gguf) | i1-Q3_K_L | 39.6 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-IQ4_XS.gguf) | i1-IQ4_XS | 39.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q4_0.gguf) | i1-Q4_0 | 41.5 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q4_K_S.gguf) | i1-Q4_K_S | 44.0 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q4_1.gguf) | i1-Q4_1 | 45.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q4_K_M.gguf) | i1-Q4_K_M | 47.5 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q5_K_S.gguf) | i1-Q5_K_S | 51.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q5_K_M.gguf) | i1-Q5_K_M | 54.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF/resolve/main/Qwen2.5-VL-72B-Instruct-heretic.i1-Q6_K.gguf) | i1-Q6_K | 64.4 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "multimodal",
    "heretic",
    "uncensored",
    "decensored",
    "abliterated",
    "en",
    "base_model:coder3101/Qwen2.5-VL-72B-Instruct-heretic",
    "base_model:quantized:coder3101/Qwen2.5-VL-72B-Instruct-heretic",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 882,
  "gated": false,
  "private": false,
  "last_modified": "2026-02-25T13:57:21.000Z",
  "created_at": "2026-02-25T10:10:11.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "699eca83251cac84be89d9e1",
  "id": "mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF",
  "modelId": "mradermacher/Qwen2.5-VL-72B-Instruct-heretic-i1-GGUF",
  "sha": "77a49cc6af178366d9b23cffb0965d434d44fa2d",
  "createdAt": "2026-02-25T10:10:11.000Z",
  "lastModified": "2026-02-25T13:57:21.000Z",
  "author": "mradermacher",
  "downloads": 882,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}