mradermacher/jais-family-30b-16k-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "inceptionai/jais-family-30b-16k",
    "language": [
      "ar",
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "quantized_by": "mradermacher",
    "tags": [
      "Arabic",
      "English",
      "LLM",
      "Decoder",
      "causal-lm",
      "jais-family"
    ],
    "frontmatter": {
      "base_model": "inceptionai/jais-family-30b-16k",
      "language": [
        "ar",
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "quantized_by": "mradermacher",
      "tags": [
        "Arabic",
        "English",
        "LLM",
        "Decoder",
        "causal-lm",
        "jais-family"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/inceptionai/jais-family-30b-16k  static quants are available at https://huggingface.co/mradermacher/jais-family-30b-16k-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: inceptionai/jais-family-30b-16k\nlanguage:\n- ar\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nquantized_by: mradermacher\ntags:\n- Arabic\n- English\n- LLM\n- Decoder\n- causal-lm\n- jais-family\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/inceptionai/jais-family-30b-16k\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/jais-family-30b-16k-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/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ1_S.gguf) | i1-IQ1_S | 18.5 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ1_M.gguf) | i1-IQ1_M | 19.0 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ2_S.gguf) | i1-IQ2_S | 21.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q2_K_S.gguf) | i1-Q2_K_S | 21.5 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ2_M.gguf) | i1-IQ2_M | 21.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q2_K.gguf) | i1-Q2_K | 21.8 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 22.9 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 23.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ3_S.gguf) | i1-IQ3_S | 23.9 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 23.9 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ3_M.gguf) | i1-IQ3_M | 25.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 25.2 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 25.5 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 26.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.1 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.0 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 30.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 31.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-i1-GGUF/resolve/main/jais-family-30b-16k.i1-Q6_K.gguf) | i1-Q6_K | 33.2 | 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",
    "Arabic",
    "English",
    "LLM",
    "Decoder",
    "causal-lm",
    "jais-family",
    "ar",
    "en",
    "base_model:inceptionai/jais-family-30b-16k",
    "base_model:quantized:inceptionai/jais-family-30b-16k",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix"
  ],
  "likes": 0,
  "downloads": 171,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-06T09:48:20.000Z",
  "created_at": "2025-03-06T07:42:52.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "67c951fc9ab6ecbd929850ab",
  "id": "mradermacher/jais-family-30b-16k-i1-GGUF",
  "modelId": "mradermacher/jais-family-30b-16k-i1-GGUF",
  "sha": "ee1017894ad98af3f317f12884bb412befa79d52",
  "createdAt": "2025-03-06T07:42:52.000Z",
  "lastModified": "2025-03-06T09:48:20.000Z",
  "author": "mradermacher",
  "downloads": 171,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 23
}