mradermacher/llama3-docchat-1.0-8b-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "cerebras/Llama3-DocChat-1.0-8B",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "other",
    "quantized_by": "mradermacher",
    "tags": [
      "cerebras",
      "doc-chat",
      "DocChat",
      "llama-3",
      "pytorch"
    ],
    "frontmatter": {
      "base_model": "cerebras/Llama3-DocChat-1.0-8B",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "other",
      "quantized_by": "mradermacher",
      "tags": [
        "cerebras",
        "doc-chat",
        "DocChat",
        "llama-3",
        "pytorch"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/cerebras/Llama3-DocChat-1.0-8B  static quants are available at https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: cerebras/Llama3-DocChat-1.0-8B\nlanguage:\n- en\nlibrary_name: transformers\nlicense: other\nquantized_by: mradermacher\ntags:\n- cerebras\n- doc-chat\n- DocChat\n- llama-3\n- pytorch\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/cerebras/Llama3-DocChat-1.0-8B\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-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/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF/resolve/main/Llama3-DocChat-1.0-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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",
    "cerebras",
    "doc-chat",
    "DocChat",
    "llama-3",
    "pytorch",
    "en",
    "base_model:cerebras/Llama3-DocChat-1.0-8B",
    "base_model:quantized:cerebras/Llama3-DocChat-1.0-8B",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 1,
  "downloads": 221,
  "gated": false,
  "private": false,
  "last_modified": "2025-01-22T01:55:39.000Z",
  "created_at": "2024-11-14T20:27:01.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "67365d159c8a98240f9232aa",
  "id": "mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF",
  "modelId": "mradermacher/Llama3-DocChat-1.0-8B-i1-GGUF",
  "sha": "698af495648514651760b0790e8ba9a1389fd781",
  "createdAt": "2024-11-14T20:27:01.000Z",
  "lastModified": "2025-01-22T01:55:39.000Z",
  "author": "mradermacher",
  "downloads": 221,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}