applispee/anima-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "other",
    "license_name": "circlestone-labs-non-commercial-license",
    "license_link": "https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.md",
    "base_model": [
      "circlestone-labs/Anima"
    ],
    "base_model_relation": "quantized",
    "frontmatter": {
      "license": "other",
      "license_name": "circlestone-labs-non-commercial-license",
      "license_link": "https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.md",
      "base_model": [
        "circlestone-labs/Anima"
      ],
      "base_model_relation": "quantized"
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/63fbf6951b4b1bd4e706fed1/BSEQSYZniROqpfqiivPmB.webp",
    "summary": "# How to use",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\nlicense_name: circlestone-labs-non-commercial-license\nlicense_link: https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.md\nbase_model:\n- circlestone-labs/Anima\nbase_model_relation: quantized\n---\n\n# GGUF models of ANIMA\n\n# How to use\n\n- **Update ComfyUI to v0.14.1 or above.** *(You don't need custom script.)*\n- Download GGUF you want. (Recommend at least Q5_K_M)\n- Use [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node to load the model.\n\n\n\n\n## Generation speed\n\nTested on\n- RTX5090(400W), ComfyUI with `--fast` option and `Patch Sage Attention KJ` node(AUTO).\n- 832x1216, cfg 5.0, 50steps\n\n| Quant  | it/s | Time (s)  | Speed vs BF16 (%) |\n| ------ | ---- | --------- | ---------------- |\n| BF16   | **4.65** | **11.70** | 0.00%        |\n| Q8_0   | *4.46* | *12.07* | -4.09%           |\n| Q6_K   | 3.60 | 14.91     | -22.58%          |\n| Q5_K_S | 3.35 | 15.94     | -28.03%          |\n| Q5_K_M | 3.41 | 15.67     | -26.67%          |\n| Q5_1   | 3.42 | 15.24     | -26.45%          |\n| Q5_0   | 3.40 | 15.73     | -26.88%          |\n| Q4_K_S | 3.55 | 15.12     | -23.66%          |\n| Q4_K_M | 3.59 | 14.98     | -22.80%          |\n| Q4_1   | 4.01 | 13.46     | -13.76%          |\n| Q4_0   | 3.97 | 13.50     | -14.62%          |\n\n## Sample\n\n### anima-preview3-base\n\n![26-04-09-Anima_00007_](https://cdn-uploads.huggingface.co/production/uploads/63fbf6951b4b1bd4e706fed1/BSEQSYZniROqpfqiivPmB.webp)\n\n### anima-preview2\n\n![26-03-12-Anima_00031_](https://cdn-uploads.huggingface.co/production/uploads/63fbf6951b4b1bd4e706fed1/XXtcZh7Au0RO8JC1A0R6A.webp)\n\n### anima-preview\n\n![Anima_GGUF_Comparison](https://cdn-uploads.huggingface.co/production/uploads/63fbf6951b4b1bd4e706fed1/mTWE0WdRsuvoJEwRMeEWr.webp)\n\n\n## How to reproduce\n\n1. Convert BF16 model to FP32\n\n```python\nimport torch\nimport safetensors.torch\nimport os\nimport sys\n\ndef convert_to_fp32(input_path, output_path):\n    state_dict = safetensors.torch.load_file(input_path)\n\n    new_state_dict = {}\n    for key, tensor in state_dict.items():\n        print(f\"{key} ({tensor.dtype}) -> torch.float32\")\n        new_tensor = tensor.to(torch.float32)\n        new_state_dict[key] = new_tensor\n\n    safetensors.torch.save_file(new_state_dict, output_path)\n    print(f\"output_path: {output_path}\")\n\nif __name__ == \"__main__\":\n    assert len(sys.argv) == 3, f\"usage: {sys.argv[0]} SOURCE TARGET\"\n    input_path, output_path = sys.argv[1:3]\n\n    convert_to_fp32(input_path, output_path)\n```\n\n2. Read [this manual](https://github.com/city96/ComfyUI-GGUF/blob/main/tools/README.md).\n3. make F32 GGUF using https://github.com/city96/ComfyUI-GGUF/blob/main/tools/convert.py#L258\n4. Run `llama-quantize`.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "base_model:circlestone-labs/Anima",
    "base_model:quantized:circlestone-labs/Anima",
    "license:other",
    "region:us"
  ],
  "likes": 0,
  "downloads": 86,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-10T13:51:07.000Z",
  "created_at": "2026-04-10T13:51:07.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69d9004bdd45825d83d28d31",
  "id": "applispee/Anima-GGUF",
  "modelId": "applispee/Anima-GGUF",
  "sha": "a4b901d5a70d00ed9b9ede79a1542c9ce5d4f9b8",
  "createdAt": "2026-04-10T13:51:07.000Z",
  "lastModified": "2026-04-10T13:51:07.000Z",
  "author": "applispee",
  "downloads": 86,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}