mradermacher/qwen1.5-72b-chat-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "Qwen/Qwen1.5-72B-Chat",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://huggingface.co/Qwen/Qwen1.5-72B-Chat/blob/main/LICENSE",
    "license_name": "tongyi-qianwen",
    "quantized_by": "mradermacher",
    "tags": [
      "chat"
    ],
    "frontmatter": {
      "base_model": "Qwen/Qwen1.5-72B-Chat",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "other",
      "license_link": "https://huggingface.co/Qwen/Qwen1.5-72B-Chat/blob/main/LICENSE",
      "license_name": "tongyi-qianwen",
      "quantized_by": "mradermacher",
      "tags": [
        "chat"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About     weighted/imatrix quants of https://huggingface.co/Qwen/Qwen1.5-72B-Chat  static quants are available at https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: Qwen/Qwen1.5-72B-Chat\nlanguage:\n- en\nlibrary_name: transformers\nlicense: other\nlicense_link: https://huggingface.co/Qwen/Qwen1.5-72B-Chat/blob/main/LICENSE\nlicense_name: tongyi-qianwen\nquantized_by: mradermacher\ntags:\n- chat\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\nweighted/imatrix quants of https://huggingface.co/Qwen/Qwen1.5-72B-Chat\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-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/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 16.3 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 17.7 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ2_S.gguf) | i1-IQ2_S | 23.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 25.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.8 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 28.6 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 30.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 31.7 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 33.0 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 34.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 36.0 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 38.6 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q4_0.gguf) | i1-Q4_0 | 41.2 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 42.0 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 44.2 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 50.0 |  |\n| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 51.4 |  |\n| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-72B-Chat-i1-GGUF/resolve/main/Qwen1.5-72B-Chat.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 59.4 | 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.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "chat",
    "en",
    "base_model:Qwen/Qwen1.5-72B-Chat",
    "base_model:quantized:Qwen/Qwen1.5-72B-Chat",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 92,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-14T19:10:41.000Z",
  "created_at": "2024-05-11T07:59:45.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "663f25716b5a9965102e64e3",
  "id": "mradermacher/Qwen1.5-72B-Chat-i1-GGUF",
  "modelId": "mradermacher/Qwen1.5-72B-Chat-i1-GGUF",
  "sha": "7929c9fa3bd3880e2d1e725b078d1351ab4e79be",
  "createdAt": "2024-05-11T07:59:45.000Z",
  "lastModified": "2024-05-14T19:10:41.000Z",
  "author": "mradermacher",
  "downloads": 92,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}