mradermacher/apertus-70b-instruct-2509-heretic-v3-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "surelio/Apertus-70B-Instruct-2509-heretic-v1.1.3",
    "extra_gated_button_content": "Submit",
    "extra_gated_fields": {
      "Affiliation": "text",
      "By clicking Submit below I accept the terms of use": "checkbox",
      "Country": "country",
      "Your Name": "text",
      "geo": "ip_location"
    },
    "extra_gated_prompt": "### Apertus LLM Acceptable Use Policy  \n(1.0 | September 1, 2025)\n\"Agreement\" The Swiss National AI Institute (SNAI) is a partnership between the two Swiss Federal Institutes of Technology, ETH Zurich and EPFL. \n\nBy using the Apertus LLM you agree to indemnify, defend, and hold harmless ETH Zurich and EPFL against any third-party claims arising from your use of Apertus LLM. \n\nThe training data and the Apertus LLM may contain or generate information that directly or indirectly refers to an identifiable individual (Personal Data). You process Personal Data as independent controller in accordance with applicable data protection law. SNAI will regularly provide a file with hash values for download which you can apply as an output filter to your use of our Apertus LLM. The file reflects data protection deletion requests which have been addressed to SNAI as the developer of the Apertus LLM. It allows you to remove Personal Data contained in the model output. We strongly advise downloading and applying this output filter from SNAI every six months following the release of the model.  ",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "multilingual",
      "compliant",
      "swiss-ai",
      "apertus",
      "heretic",
      "uncensored",
      "decensored",
      "abliterated"
    ],
    "frontmatter": {
      "base_model": "surelio/Apertus-70B-Instruct-2509-heretic-v1.1.3",
      "extra_gated_button_content": "Submit",
      "extra_gated_fields": [],
      "extra_gated_prompt": "\"### Apertus LLM Acceptable Use Policy  \\n(1.0 | September 1,",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "multilingual",
        "compliant",
        "swiss-ai",
        "apertus",
        "heretic",
        "uncensored",
        "decensored",
        "abliterated"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         static quants of https://huggingface.co/surelio/Apertus-70B-Instruct-2509-heretic-v1.1.3  ***For a convenient overview and download list, visit our model page for this model.*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-i1-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: surelio/Apertus-70B-Instruct-2509-heretic-v1.1.3\nextra_gated_button_content: Submit\nextra_gated_fields:\n  Affiliation: text\n  By clicking Submit below I accept the terms of use: checkbox\n  Country: country\n  Your Name: text\n  geo: ip_location\nextra_gated_prompt: \"### Apertus LLM Acceptable Use Policy  \\n(1.0 | September 1,\n  2025)\\n\\\"Agreement\\\" The Swiss National AI Institute (SNAI) is a partnership between\n  the two Swiss Federal Institutes of Technology, ETH Zurich and EPFL. \\n\\nBy using\n  the Apertus LLM you agree to indemnify, defend, and hold harmless ETH Zurich and\n  EPFL against any third-party claims arising from your use of Apertus LLM. \\n\\nThe\n  training data and the Apertus LLM may contain or generate information that directly\n  or indirectly refers to an identifiable individual (Personal Data). You process\n  Personal Data as independent controller in accordance with applicable data protection\n  law. SNAI will regularly provide a file with hash values for download which you\n  can apply as an output filter to your use of our Apertus LLM. The file reflects\n  data protection deletion requests which have been addressed to SNAI as the developer\n  of the Apertus LLM. It allows you to remove Personal Data contained in the model\n  output. We strongly advise downloading and applying this output filter from SNAI\n  every six months following the release of the model.  \"\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- multilingual\n- compliant\n- swiss-ai\n- apertus\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:  -->\n<!-- ### quants:  x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->\n<!-- ### quants_skip:  -->\n<!-- ### skip_mmproj:  -->\nstatic quants of https://huggingface.co/surelio/Apertus-70B-Instruct-2509-heretic-v1.1.3\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#Apertus-70B-Instruct-2509-heretic-v3-GGUF).***\n\nweighted/imatrix quants are available at https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-i1-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/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q2_K.gguf) | Q2_K | 27.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q3_K_S.gguf) | Q3_K_S | 30.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q3_K_M.gguf) | Q3_K_M | 35.6 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.IQ4_XS.gguf) | IQ4_XS | 38.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q3_K_L.gguf) | Q3_K_L | 39.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q4_K_S.gguf) | Q4_K_S | 40.5 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q4_K_M.gguf) | Q4_K_M | 43.8 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q5_K_S.gguf) | Q5_K_S | 48.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q5_K_M.gguf) | Q5_K_M | 50.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q6_K.gguf) | Q6_K | 58.0 | very good quality |\n| [GGUF](https://huggingface.co/mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF/resolve/main/Apertus-70B-Instruct-2509-heretic-v3.Q8_0.gguf) | Q8_0 | 75.1 | fast, best quality |\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.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "multilingual",
    "compliant",
    "swiss-ai",
    "apertus",
    "heretic",
    "uncensored",
    "decensored",
    "abliterated",
    "en",
    "base_model:surelio/Apertus-70B-Instruct-2509-heretic-v1.1.3",
    "base_model:quantized:surelio/Apertus-70B-Instruct-2509-heretic-v1.1.3",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 1195,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-08T15:53:53.000Z",
  "created_at": "2026-04-03T14:51:56.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "69cfd40cdc51445bfae99b7a",
  "id": "mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF",
  "modelId": "mradermacher/Apertus-70B-Instruct-2509-heretic-v3-GGUF",
  "sha": "b39f71d738d3d34e6d1daad9e292059de6aac7c1",
  "createdAt": "2026-04-03T14:51:56.000Z",
  "lastModified": "2026-04-08T15:53:53.000Z",
  "author": "mradermacher",
  "downloads": 1195,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 13
}