jiaojjjjje/qwen3.5-35b-a3b-abliterated-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "base_model": "Qwen/Qwen3.5-35B-A3B",
    "tags": [
      "abliterated",
      "uncensored",
      "qwen3.5",
      "moe",
      "gguf"
    ],
    "language": [
      "en",
      "zh"
    ],
    "pipeline_tag": "text-generation",
    "frontmatter": {
      "license": "apache-2.0",
      "base_model": "Qwen/Qwen3.5-35B-A3B",
      "tags": [
        "abliterated",
        "uncensored",
        "qwen3.5",
        "moe",
        "gguf"
      ],
      "language": [
        "en",
        "zh"
      ],
      "pipeline_tag": "text-generation"
    },
    "hero_image_url": "",
    "summary": "GGUF quantization of jiaojjjjje/Qwen3.5-35B-A3B-abliterated. This is an **abliterated (uncensored)** version of Qwen3.5-35B-A3B (v9c). The model's refusal behavior has been removed using asymmetric layer tapering abliteration. > **Warning**: This model is completely uncensored. Use responsibly and at your own risk.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nbase_model: Qwen/Qwen3.5-35B-A3B\ntags:\n  - abliterated\n  - uncensored\n  - qwen3.5\n  - moe\n  - gguf\nlanguage:\n  - en\n  - zh\npipeline_tag: text-generation\n---\n\n# Qwen3.5-35B-A3B-abliterated-GGUF\n\nGGUF quantization of [jiaojjjjje/Qwen3.5-35B-A3B-abliterated](https://huggingface.co/jiaojjjjje/Qwen3.5-35B-A3B-abliterated).\n\nThis is an **abliterated (uncensored)** version of Qwen3.5-35B-A3B (v9c). The model's refusal behavior has been removed using asymmetric layer tapering abliteration.\n\n> **Warning**: This model is completely uncensored. Use responsibly and at your own risk.\n\n## Available Quantizations\n\n| File | Quant | Size | Description |\n|---|---|---|---|\n| Qwen3.5-35B-A3B-abliterated-Q8_0.gguf | Q8_0 | ~34 GB | High quality, near-lossless |\n\n## Key Features (v9c)\n\n- **Effective uncensoring**: NSFW, political, and other restricted content generation works reliably\n- **No long-text repetition**: Tested stable at 11000+ characters with asymmetric layer tapering\n- **Thinking mode disabled**: Chat template modified to skip `<think>` blocks by default\n\n## Usage\n\n### LM Studio\n\n1. Download the GGUF file\n2. Place it in your LM Studio models directory\n3. Load with context length 4096+\n\n### llama.cpp\n\n```bash\n./llama-cli -m Qwen3.5-35B-A3B-abliterated-Q8_0.gguf -p \"Hello!\" -n 256\n```\n\n## Details\n\nSee the full model card at [jiaojjjjje/Qwen3.5-35B-A3B-abliterated](https://huggingface.co/jiaojjjjje/Qwen3.5-35B-A3B-abliterated) for abliteration details, hyperparameters, and evaluation.\n\n## Disclaimer\n\nThis model is provided for **research and educational purposes only**. The creator is not responsible for any misuse.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "abliterated",
    "uncensored",
    "qwen3.5",
    "moe",
    "text-generation",
    "en",
    "zh",
    "base_model:Qwen/Qwen3.5-35B-A3B",
    "base_model:quantized:Qwen/Qwen3.5-35B-A3B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 209,
  "gated": false,
  "private": false,
  "last_modified": "2026-02-27T18:38:46.000Z",
  "created_at": "2026-02-27T08:42:55.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "69a1590fb50688db5168131a",
  "id": "jiaojjjjje/Qwen3.5-35B-A3B-abliterated-GGUF",
  "modelId": "jiaojjjjje/Qwen3.5-35B-A3B-abliterated-GGUF",
  "sha": "ae20b01849ddba706eb05cb58fb9381578984a8e",
  "createdAt": "2026-02-27T08:42:55.000Z",
  "lastModified": "2026-02-27T18:38:46.000Z",
  "author": "jiaojjjjje",
  "downloads": 209,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 3
}