mradermacher/titulm-llama-3.2-3b-v1.1-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "hishab/titulm-llama-3.2-3b-v1.1",
    "language": [
      "bn"
    ],
    "library_name": "transformers",
    "license": "llama3.2",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "hishab",
      "titulm",
      "pytorch",
      "llama",
      "llama-3",
      "llama-factory"
    ],
    "frontmatter": {
      "base_model": "hishab/titulm-llama-3.2-3b-v1.1",
      "language": [
        "bn"
      ],
      "library_name": "transformers",
      "license": "llama3.2",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "hishab",
        "titulm",
        "pytorch",
        "llama",
        "llama-3",
        "llama-factory"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/hishab/titulm-llama-3.2-3b-v1.1  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: hishab/titulm-llama-3.2-3b-v1.1\nlanguage:\n- bn\nlibrary_name: transformers\nlicense: llama3.2\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- hishab\n- titulm\n- pytorch\n- llama\n- llama-3\n- llama-factory\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/hishab/titulm-llama-3.2-3b-v1.1\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#titulm-llama-3.2-3b-v1.1-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-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/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF/resolve/main/titulm-llama-3.2-3b-v1.1.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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",
    "hishab",
    "titulm",
    "pytorch",
    "llama",
    "llama-3",
    "llama-factory",
    "bn",
    "base_model:hishab/titulm-llama-3.2-3b-v1.1",
    "base_model:quantized:hishab/titulm-llama-3.2-3b-v1.1",
    "license:llama3.2",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 94,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-11T08:39:51.000Z",
  "created_at": "2025-03-19T12:25:16.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "67dab7aca8d343876d6b1884",
  "id": "mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF",
  "modelId": "mradermacher/titulm-llama-3.2-3b-v1.1-i1-GGUF",
  "sha": "f54a6e92c694b6c6992e656074158b068a1e0510",
  "createdAt": "2025-03-19T12:25:16.000Z",
  "lastModified": "2025-07-11T08:39:51.000Z",
  "author": "mradermacher",
  "downloads": 94,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}