nuofang/qwen3.5-9b-claude-4.6-opus-deckard-v4.2-uncensored-heretic-thinking-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking",
    "tags": [
      "llama.cpp",
      "quantized",
      "imatrix"
    ],
    "frontmatter": {
      "base_model": "DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking",
      "tags": [
        "llama.cpp",
        "quantized",
        "imatrix"
      ]
    },
    "hero_image_url": "",
    "summary": "# Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking GGUF This repository contains GGUF format model files for DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking. IQ4_XS: Compressed to the minimum footprint with only a slight degradation in quality. Q5_K_M: Moderately compressed and effectively leverages the imatrix, making it nearly indistinguishable from the original precision. The calibration data for the imatrix is targeted at Chinese novels and role-playing (RP), while preserving logic and common sense. IQ4_XS: 在只有轻微质量下降的情况下，压缩到最小占用。 Q5_K_M: 适度压缩且发挥了imatrix的作用，难以察觉到与原精度的区别。 imatrix 的校准数据以中文的小说、角色扮演为目标，同时保留逻辑和常识。",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking\ntags:\n- llama.cpp\n- quantized\n- imatrix\n---\n# Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking GGUF\nThis repository contains GGUF format model files for [DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking](https://huggingface.co/DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking).\n\nIQ4_XS: Compressed to the minimum footprint with only a slight degradation in quality.  \nQ5_K_M: Moderately compressed and effectively leverages the imatrix, making it nearly indistinguishable from the original precision.  \nThe calibration data for the imatrix is targeted at Chinese novels and role-playing (RP), while preserving logic and common sense.  \n\nIQ4_XS: 在只有轻微质量下降的情况下，压缩到最小占用。  \nQ5_K_M: 适度压缩且发挥了imatrix的作用，难以察觉到与原精度的区别。  \nimatrix 的校准数据以中文的小说、角色扮演为目标，同时保留逻辑和常识。  \n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "llama.cpp",
    "quantized",
    "imatrix",
    "base_model:DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking",
    "base_model:quantized:DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 1603,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-21T15:34:47.000Z",
  "created_at": "2026-03-18T07:39:50.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69ba56c6e08fed62c3998283",
  "id": "nuofang/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking-GGUF",
  "modelId": "nuofang/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking-GGUF",
  "sha": "0c97bab3d8acdff4eaa1794d7be187e0effef88a",
  "createdAt": "2026-03-18T07:39:50.000Z",
  "lastModified": "2026-03-21T15:34:47.000Z",
  "author": "nuofang",
  "downloads": 1603,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 6
}