mradermacher/mistral-2x22b-moe-power-codestral-ultimate-39b-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "DavidAU/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://mistral.ai/licences/MNPL-0.1.md",
    "license_name": "mnpl",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "merge",
      "programming",
      "code generation",
      "Codestral",
      "code",
      "moe",
      "coding",
      "coder",
      "chat",
      "mistral",
      "mixtral",
      "mixture of experts",
      "mistral moe",
      "2X22B"
    ],
    "frontmatter": {
      "base_model": "DavidAU/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "other",
      "license_link": "https://mistral.ai/licences/MNPL-0.1.md",
      "license_name": "mnpl",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "merge",
        "programming",
        "code generation",
        "Codestral",
        "code",
        "moe",
        "coding",
        "coder",
        "chat",
        "mistral",
        "mixtral",
        "mixture of experts",
        "mistral moe",
        "2X22B"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/DavidAU/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: DavidAU/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B\nlanguage:\n- en\nlibrary_name: transformers\nlicense: other\nlicense_link: https://mistral.ai/licences/MNPL-0.1.md\nlicense_name: mnpl\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- merge\n- programming\n- code generation\n- Codestral\n- code\n- moe\n- coding\n- coder\n- chat\n- mistral\n- mixtral\n- mixture of experts\n- mistral moe\n- 2X22B\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/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B\n\n<!-- provided-files -->\n\n***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-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/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ1_S.gguf) | i1-IQ1_S | 8.3 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ1_M.gguf) | i1-IQ1_M | 9.1 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 10.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 11.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ2_S.gguf) | i1-IQ2_S | 12.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ2_M.gguf) | i1-IQ2_M | 13.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 13.5 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q2_K.gguf) | i1-Q2_K | 14.5 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 15.2 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 16.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 17.0 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ3_S.gguf) | i1-IQ3_S | 17.1 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ3_M.gguf) | i1-IQ3_M | 17.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 18.9 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 20.6 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 21.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q4_0.gguf) | i1-Q4_0 | 22.3 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 22.4 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 23.7 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q4_1.gguf) | i1-Q4_1 | 24.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 27.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 27.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF/resolve/main/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B.i1-Q6_K.gguf) | i1-Q6_K | 32.2 | 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",
    "merge",
    "programming",
    "code generation",
    "Codestral",
    "code",
    "moe",
    "coding",
    "coder",
    "chat",
    "mistral",
    "mixtral",
    "mixture of experts",
    "mistral moe",
    "2X22B",
    "en",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 1,
  "downloads": 255,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-15T17:00:23.000Z",
  "created_at": "2025-07-15T12:37:59.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "68764ba72291f598aa4a45ad",
  "id": "mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF",
  "modelId": "mradermacher/Mistral-2x22B-MOE-Power-Codestral-Ultimate-39B-i1-GGUF",
  "sha": "6029f316080f0c42e3cd024164740107b66e9b92",
  "createdAt": "2025-07-15T12:37:59.000Z",
  "lastModified": "2025-07-15T17:00:23.000Z",
  "author": "mradermacher",
  "downloads": 255,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}