mradermacher/qwen3.5-35b-a3b-heretic-v2-eq-v1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "nivvis/Qwen3.5-35B-A3B-EQ-v1",
    "datasets": [
      "nivvis/eq-dpo"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "model_type": "qwen3_5_moe",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "qwen3.5",
      "moe",
      "dpo",
      "abliterated",
      "emotional-intelligence",
      "eq-bench",
      "empathy",
      "bfloat16"
    ],
    "frontmatter": {
      "base_model": "nivvis/Qwen3.5-35B-A3B-EQ-v1",
      "datasets": [
        "nivvis/eq-dpo"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "model_type": "qwen3_5_moe",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "qwen3.5",
        "moe",
        "dpo",
        "abliterated",
        "emotional-intelligence",
        "eq-bench",
        "empathy",
        "bfloat16"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         static quants of https://huggingface.co/nivvis/Qwen3.5-35B-A3B-EQ-v1  ***For a convenient overview and download list, visit our model page for this model.*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-i1-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: nivvis/Qwen3.5-35B-A3B-EQ-v1\ndatasets:\n- nivvis/eq-dpo\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nmodel_type: qwen3_5_moe\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- qwen3.5\n- moe\n- dpo\n- abliterated\n- emotional-intelligence\n- eq-bench\n- empathy\n- bfloat16\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/nivvis/Qwen3.5-35B-A3B-EQ-v1\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#Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF).***\n\nweighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-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/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q2_K.gguf) | Q2_K | 13.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q3_K_S.gguf) | Q3_K_S | 15.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q3_K_M.gguf) | Q3_K_M | 16.9 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q3_K_L.gguf) | Q3_K_L | 18.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.IQ4_XS.gguf) | IQ4_XS | 19.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q4_K_S.gguf) | Q4_K_S | 20.0 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q4_K_M.gguf) | Q4_K_M | 21.3 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q5_K_S.gguf) | Q5_K_S | 24.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q5_K_M.gguf) | Q5_K_M | 24.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q6_K.gguf) | Q6_K | 28.6 | very good quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-eq-v1.Q8_0.gguf) | Q8_0 | 37.0 | 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",
    "qwen3.5",
    "moe",
    "dpo",
    "abliterated",
    "emotional-intelligence",
    "eq-bench",
    "empathy",
    "bfloat16",
    "en",
    "dataset:nivvis/eq-dpo",
    "base_model:nivvis/Qwen3.5-35B-A3B-EQ-v1",
    "base_model:quantized:nivvis/Qwen3.5-35B-A3B-EQ-v1",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 2532,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-29T09:50:19.000Z",
  "created_at": "2026-03-20T08:03:54.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "69bcff6a9bf0af8ee4709aed",
  "id": "mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF",
  "modelId": "mradermacher/Qwen3.5-35B-A3B-heretic-v2-eq-v1-GGUF",
  "sha": "0cff6fbfd57c7479c247a72f24e760b01dd30945",
  "createdAt": "2026-03-20T08:03:54.000Z",
  "lastModified": "2026-03-29T09:50:19.000Z",
  "author": "mradermacher",
  "downloads": 2532,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 15
}