lewdiculous/captainerisnebula-12b-chimera-v1.1-gguf-iq-imatrix overview

{
  "metadata": {},
  "card_data": {
    "license": "other",
    "license_link": "LICENSE",
    "base_model": [
      "Nitral-AI/CaptainErisNebula-12B-Chimera-v1.1"
    ],
    "tags": [
      "text-generation-inference",
      "testing",
      "mistral",
      "chatml"
    ],
    "frontmatter": {
      "license": "other",
      "license_link": "LICENSE",
      "base_model": [
        "Nitral-AI/CaptainErisNebula-12B-Chimera-v1.1"
      ],
      "tags": [
        "text-generation-inference",
        "testing",
        "mistral",
        "chatml"
      ]
    },
    "hero_image_url": "https://iili.io/KKtCMf2.md.jpg",
    "summary": "release version at the time: b6258. # Imatrix was based on the full ... FP16 precision GGUF. START: BF16 HuggingFace Model ↓ (1) Conversion to Full-Precision GGUF ↓ FP16 GGUF (for Calibration Imatrix) BF16 GGUF (for Quantization) ↓ (2) Generate Imatrix (from FP16 GGUF) ↓ imatrix.fp16.gguf ↓ (3) Quantize with Imatrix (using BF16 GGUF) ↓ Final Quantized GGUF Models ↓ END ```",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\nlicense_link: LICENSE\nbase_model:\n- Nitral-AI/CaptainErisNebula-12B-Chimera-v1.1\ntags:\n- text-generation-inference\n- testing\n- mistral\n- chatml\n---\n\n> [!TIP]\n> # **GGUF quants for [**Nitral-AI/CaptainErisNebula-12B-Chimera-v1.1**](https://huggingface.co/Nitral-AI/CaptainErisNebula-12B-Chimera-v1.1)'s recipe.**\n\n> [!IMPORTANT]\n> **Author recommended initial SillyTavern presets:** <br>\n> - [Chimera: v1.1](https://huggingface.co/Nitral-AI/CaptainErisNebula-12B-Chimera-v1.1/tree/main/ST)\n>   - [(backup)(633788596ef1810cc9ea9abd375bbda3e568bd37)](https://huggingface.co/Lewdiculous/CaptainErisNebula-12B-Chimera-v1.1-GGUF-IQ-Imatrix/tree/main/sillytavern)\n\n![https://iili.io/KKtCMf2.md.jpg](https://iili.io/KKtCMf2.md.jpg)\n\n<hr>\n\n> [!NOTE]\n> ## This is an improvement on the previous experimental version. <br>\n> - Not \"chaotic\", and at a usable size for most people seeking to perform inference locally with good speeds. <br>\n> - The model does not show excessive alignment, so it should be good for most scenarios/writing situations. <br> <br>\n> - Feel free to use some light system prompting to nudge it out of a blocker if needed. <br> <br>\n> - It does well in adhering to characters and instructions. <br> <br>\n\n<hr>\n\nThank you so much, \"crazy chef\" and \"mad scientist\", **Nitral**!\n\n<!-- ![red nebula inspired model card image](https://iili.io/KJuO2Ie.png) -->\n\n<br>\n\n```text\n# Using the latest llama.cpp ...\nrelease version at the time: b6258.\n# Imatrix was based on the full ...\nFP16 precision GGUF.\n\nSTART: BF16 HuggingFace Model\n↓\n(1) Conversion to Full-Precision GGUF\n↓\nFP16 GGUF (for Calibration Imatrix)\nBF16 GGUF (for Quantization)\n↓\n(2) Generate Imatrix (from FP16 GGUF)\n↓\nimatrix.fp16.gguf\n↓\n(3) Quantize with Imatrix (using BF16 GGUF)\n↓\nFinal Quantized GGUF Models\n↓\nEND\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-generation-inference",
    "testing",
    "mistral",
    "chatml",
    "base_model:Nitral-AI/CaptainErisNebula-12B-Chimera-v1.1",
    "base_model:quantized:Nitral-AI/CaptainErisNebula-12B-Chimera-v1.1",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 22,
  "downloads": 3135,
  "gated": false,
  "private": false,
  "last_modified": "2025-08-31T19:16:00.000Z",
  "created_at": "2025-08-24T08:05:24.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "68aac7c4d396e91c5afa9c50",
  "id": "Lewdiculous/CaptainErisNebula-12B-Chimera-v1.1-GGUF-IQ-Imatrix",
  "modelId": "Lewdiculous/CaptainErisNebula-12B-Chimera-v1.1-GGUF-IQ-Imatrix",
  "sha": "1cc7d02809945f5800641f2ba7cd1f28a67bd839",
  "createdAt": "2025-08-24T08:05:24.000Z",
  "lastModified": "2025-08-31T19:16:00.000Z",
  "author": "Lewdiculous",
  "downloads": 3135,
  "likes": 22,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 23
}