noctrex/huihui-qwen3.5-35b-a3b-abliterated-mxfp4_moe-gguf overview

{
  "metadata": {},
  "card_data": {
    "pipeline_tag": "image-text-to-text",
    "base_model": [
      "huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated"
    ],
    "frontmatter": {
      "pipeline_tag": "image-text-to-text",
      "base_model": [
        "huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated"
      ]
    },
    "hero_image_url": "",
    "summary": "These are quantizations of the model Huihui-Qwen3.5-35B-A3B-abliterated Read the guide from unsloth in order to set up the model's recommended settings: Qwen3.5 - How to Run Locally Guide The mainline standard is to use MXFP4 for the MoE tensors, and Q8 for the rest. So I created a new variant, where the other tensors are BF16 instead of Q8. On some architectures BF16 will be slower, but its the highest quality, essentialy its the original tensors from the model copied over unquantized. As of 2026-03-03 the chat template has been updated, and is using the fixed version from unsloth. If you don't want to download the model again, you can just update the chat template.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\npipeline_tag: image-text-to-text\nbase_model:\n- huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated\n---\nThese are quantizations of the model [Huihui-Qwen3.5-35B-A3B-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated)\n\n- Download the latest [llama.cpp](https://github.com/ggml-org/llama.cpp) to use these quantizations.  \n- For the `mmproj` file, the F32 version is recommended for best results.  \n- Order of quality: F32 > BF16 > F16  \n\nRead the guide from unsloth in order to set up the model's recommended settings:  \n[Qwen3.5 - How to Run Locally Guide](https://unsloth.ai/docs/models/qwen3.5)\n\nThe mainline standard is to use MXFP4 for the MoE tensors, and Q8 for the rest.  \nSo I created a new variant, where the other tensors are BF16 instead of Q8.  \nOn some architectures BF16 will be slower, but its the highest quality, essentialy its the original tensors from the model copied over unquantized.\n\nAs of 2026-03-03 the chat template has been updated, and is using the fixed version from unsloth.  \nIf you don't want to download the model again, you can just update the chat template.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "image-text-to-text",
    "base_model:huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated",
    "base_model:quantized:huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 11,
  "downloads": 2895,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-03T10:01:27.000Z",
  "created_at": "2026-02-27T13:42:16.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": ""
}

{
  "_id": "69a19f38111a0fa5ed84ede7",
  "id": "noctrex/Huihui-Qwen3.5-35B-A3B-abliterated-MXFP4_MOE-GGUF",
  "modelId": "noctrex/Huihui-Qwen3.5-35B-A3B-abliterated-MXFP4_MOE-GGUF",
  "sha": "035c3b2524a020dd8984c9384a8350d3dd4193e9",
  "createdAt": "2026-02-27T13:42:16.000Z",
  "lastModified": "2026-03-03T10:01:27.000Z",
  "author": "noctrex",
  "downloads": 2895,
  "likes": 11,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "",
  "siblings_count": 6
}