cesarsal1nas/huihui-qwen3.5-35b-a3b-abliterated-q4_k_m-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated",
    "tags": [
      "gguf",
      "abliterated",
      "uncensored",
      "conversational",
      "qwen3_5_moe",
      "llama-cpp"
    ],
    "library_name": "gguf",
    "license": "apache-2.0",
    "frontmatter": {
      "base_model": "huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated",
      "tags": [
        "gguf",
        "abliterated",
        "uncensored",
        "conversational",
        "qwen3_5_moe",
        "llama-cpp"
      ],
      "library_name": "gguf",
      "license": "apache-2.0"
    },
    "hero_image_url": "",
    "summary": "This is a Q4_K_M GGUF quantization of huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated. Refer to the original model card for full details, usage warnings, and licensing information.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated\ntags:\n- gguf\n- abliterated\n- uncensored\n- conversational\n- qwen3_5_moe\n- llama-cpp\nlibrary_name: gguf\nlicense: apache-2.0\n---\n\n> [!WARNING]\n> **A significantly improved version of this model is available.**\n>\n> This repo quantizes [huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated) — the standard abliteration.\n> A newer fine-tune of the same architecture, trained in the style of Claude 4.6 Opus, has since been released and produces noticeably richer, more expressive outputs.\n>\n> **➡️ Recommended upgrade: [Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-Q4_K_M-GGUF](https://huggingface.co/cesarsal1nas/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-Q4_K_M-GGUF)**\n>\n> Same architecture, same Q4_K_M quantization, same VRAM footprint — just a better fine-tune. This repo will remain available for reference.\n\n\n\n# Huihui-Qwen3.5-35B-A3B-abliterated — Q4_K_M GGUF\n\nThis is a Q4_K_M GGUF quantization of [huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated).\n\nRefer to the [original model card](https://huggingface.co/huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated) for full details, usage warnings, and licensing information.\n\n## Details\n\n| Property | Value |\n|---|---|\n| Source model | [huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated) |\n| Architecture | qwen35moe (35B total params, ~3B active; 256 experts, 8 active per token) |\n| Quantization | Q4_K_M (~4.8 BPW) |\n| File size | ~21 GB |\n| Quantized with | [llama.cpp](https://github.com/ggerganov/llama.cpp) |\n\n## Usage with llama.cpp\n\n```bash\nllama-cli \\\n  --hf-repo cesarsal1nas/Huihui-Qwen3.5-35B-A3B-abliterated-Q4_K_M-GGUF \\\n  --hf-file huihui-qwen3.5-35b-a3b-abliterated-Q4_K_M.gguf \\\n  -p \"Tell me about the universe\"\n```\n\n```bash\nllama-server \\\n  --hf-repo cesarsal1nas/Huihui-Qwen3.5-35B-A3B-abliterated-Q4_K_M-GGUF \\\n  --hf-file huihui-qwen3.5-35b-a3b-abliterated-Q4_K_M.gguf \\\n  -c 8192\n```\n\n## Usage with Ollama\n\nRequires Ollama with qwen35moe support. See [PR #14506](https://github.com/ollama/ollama/pull/14506) for the architecture patch.\n\n```bash\nollama run hf.co/cesarsal1nas/Huihui-Qwen3.5-35B-A3B-abliterated-Q4_K_M-GGUF\n```\n\n## Credits\n\n- **Abliteration** by [huihui-ai](https://huggingface.co/huihui-ai) — [Huihui-Qwen3.5-35B-A3B-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated)\n- **Base model** by [Qwen](https://huggingface.co/Qwen) — [Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B)\n- **Quantization** by [cesarsal1nas](https://huggingface.co/cesarsal1nas)\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "abliterated",
    "uncensored",
    "conversational",
    "qwen3_5_moe",
    "llama-cpp",
    "base_model:huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated",
    "base_model:quantized:huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 2,
  "downloads": 751,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-17T08:40:26.000Z",
  "created_at": "2026-02-28T06:26:45.000Z",
  "pipeline_tag": "",
  "library_name": "gguf"
}

{
  "_id": "69a28aa50bba8f159c53877c",
  "id": "cesarsal1nas/Huihui-Qwen3.5-35B-A3B-abliterated-Q4_K_M-GGUF",
  "modelId": "cesarsal1nas/Huihui-Qwen3.5-35B-A3B-abliterated-Q4_K_M-GGUF",
  "sha": "34e36e0098b93686d6c29b06a8a6cb4049d4ba69",
  "createdAt": "2026-02-28T06:26:45.000Z",
  "lastModified": "2026-03-17T08:40:26.000Z",
  "author": "cesarsal1nas",
  "downloads": 751,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "gguf",
  "siblings_count": 3
}