mradermacher/anki-qwen-2.5-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "anktechsol/anki-2.5",
    "datasets": [
      "ai4bharat/indic-corpus",
      "indicnlp/hindi-corpus",
      "custom-indian-datasets"
    ],
    "language": [
      "en",
      "hi",
      "bn",
      "ta",
      "te",
      "ur",
      "gu",
      "kn",
      "ml",
      "pa",
      "or",
      "as",
      "mr"
    ],
    "library_name": "transformers",
    "license": "mit",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "indian-languages",
      "conversational-ai",
      "localized-ai",
      "indic-nlp",
      "multilingual",
      "hindi",
      "bengali",
      "tamil",
      "telugu",
      "urdu",
      "gujarati",
      "kannada",
      "malayalam",
      "punjabi",
      "odia",
      "assamese",
      "marathi"
    ],
    "frontmatter": {
      "base_model": "anktechsol/anki-2.5",
      "datasets": [
        "ai4bharat/indic-corpus",
        "indicnlp/hindi-corpus",
        "custom-indian-datasets"
      ],
      "language": [
        "en",
        "hi",
        "bn",
        "ta",
        "te",
        "ur",
        "gu",
        "kn",
        "ml",
        "pa",
        "or",
        "as",
        "mr"
      ],
      "library_name": "transformers",
      "license": "mit",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "indian-languages",
        "conversational-ai",
        "localized-ai",
        "indic-nlp",
        "multilingual",
        "hindi",
        "bengali",
        "tamil",
        "telugu",
        "urdu",
        "gujarati",
        "kannada",
        "malayalam",
        "punjabi",
        "odia",
        "assamese",
        "marathi"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/anktechsol/anki-2.5  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/anki-qwen-2.5-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: anktechsol/anki-2.5\ndatasets:\n- ai4bharat/indic-corpus\n- indicnlp/hindi-corpus\n- custom-indian-datasets\nlanguage:\n- en\n- hi\n- bn\n- ta\n- te\n- ur\n- gu\n- kn\n- ml\n- pa\n- or\n- as\n- mr\nlibrary_name: transformers\nlicense: mit\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- indian-languages\n- conversational-ai\n- localized-ai\n- indic-nlp\n- multilingual\n- hindi\n- bengali\n- tamil\n- telugu\n- urdu\n- gujarati\n- kannada\n- malayalam\n- punjabi\n- odia\n- assamese\n- marathi\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags: nicoboss -->\n<!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->\n<!-- ### quants_skip:  -->\n<!-- ### skip_mmproj:  -->\nweighted/imatrix quants of https://huggingface.co/anktechsol/anki-2.5\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#anki-qwen-2.5-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/anki-qwen-2.5-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/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/anki-qwen-2.5-i1-GGUF/resolve/main/anki-qwen-2.5.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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",
    "indian-languages",
    "conversational-ai",
    "localized-ai",
    "indic-nlp",
    "multilingual",
    "hindi",
    "bengali",
    "tamil",
    "telugu",
    "urdu",
    "gujarati",
    "kannada",
    "malayalam",
    "punjabi",
    "odia",
    "assamese",
    "marathi",
    "en",
    "hi",
    "bn",
    "ta",
    "te",
    "ur",
    "gu",
    "kn",
    "ml",
    "pa",
    "or",
    "as",
    "mr",
    "dataset:ai4bharat/indic-corpus",
    "dataset:indicnlp/hindi-corpus",
    "dataset:custom-indian-datasets",
    "base_model:anktechsol/anki-2.5",
    "base_model:quantized:anktechsol/anki-2.5",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 479,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-23T04:40:32.000Z",
  "created_at": "2025-08-28T21:48:42.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "68b0cebad5a9c0522abef1f2",
  "id": "mradermacher/anki-qwen-2.5-i1-GGUF",
  "modelId": "mradermacher/anki-qwen-2.5-i1-GGUF",
  "sha": "65528e289aab883bd8eae7c64b956be9a2b8d2a2",
  "createdAt": "2025-08-28T21:48:42.000Z",
  "lastModified": "2025-12-23T04:40:32.000Z",
  "author": "mradermacher",
  "downloads": 479,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}