mradermacher/l3.2-8x4b-moe-v2-dark-champion-inst-21b-uncen-ablit-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "quantized_by": "mradermacher",
    "tags": [
      "Llama 3.2",
      "8 X 4B",
      "Brainstorm 5x",
      "128k context",
      "moe",
      "8 experts",
      "mixture of experts",
      "fine tune"
    ],
    "frontmatter": {
      "base_model": "DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "quantized_by": "mradermacher",
      "tags": [
        "Llama 3.2",
        "8 X 4B",
        "Brainstorm 5x",
        "128k context",
        "moe",
        "8 experts",
        "mixture of experts",
        "fine tune"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit  static quants are available at https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit\nlanguage:\n- en\nlibrary_name: transformers\nquantized_by: mradermacher\ntags:\n- Llama 3.2\n- 8 X 4B\n- Brainstorm 5x\n- 128k context\n- moe\n- 8 experts\n- mixture of experts\n- fine tune\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags: nicoboss -->\nweighted/imatrix quants of https://huggingface.co/DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-GGUF\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ1_S.gguf) | i1-IQ1_S | 4.8 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ1_M.gguf) | i1-IQ1_M | 5.2 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ2_S.gguf) | i1-IQ2_S | 6.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ2_M.gguf) | i1-IQ2_M | 7.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q2_K_S.gguf) | i1-Q2_K_S | 7.5 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q2_K.gguf) | i1-Q2_K | 8.1 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.5 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ3_XS.gguf) | i1-IQ3_XS | 9.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ3_S.gguf) | i1-IQ3_S | 9.5 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.5 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ3_M.gguf) | i1-IQ3_M | 9.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.4 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.0 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q4_0.gguf) | i1-Q4_0 | 12.1 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.2 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.0 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q4_1.gguf) | i1-Q4_1 | 13.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q5_K_S.gguf) | i1-Q5_K_S | 14.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q5_K_M.gguf) | i1-Q5_K_M | 15.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF/resolve/main/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit.i1-Q6_K.gguf) | i1-Q6_K | 17.3 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "Llama 3.2",
    "8 X 4B",
    "Brainstorm 5x",
    "128k context",
    "moe",
    "8 experts",
    "mixture of experts",
    "fine tune",
    "en",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 1,
  "downloads": 2400,
  "gated": false,
  "private": false,
  "last_modified": "2025-02-22T09:09:28.000Z",
  "created_at": "2025-02-16T16:02:15.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "67b20c07ce03f9a05701a2ea",
  "id": "mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF",
  "modelId": "mradermacher/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUF",
  "sha": "a4eb37421087a0b8e5f771a69c8aeda28d1ed0e3",
  "createdAt": "2025-02-16T16:02:15.000Z",
  "lastModified": "2025-02-22T09:09:28.000Z",
  "author": "mradermacher",
  "downloads": 2400,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}