mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "Thermostatic/neuraltranslate-27b-mt-nah-es-v1.2",
    "datasets": [
      "Thermostatic/Axolotl-Spanish-Nahuatl-ShareGPT-Filtered-Splits"
    ],
    "language": [
      "es",
      "nah"
    ],
    "library_name": "transformers",
    "license": "mit",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "Translation",
      "Gemma 3",
      "Spanish",
      "Nahuatl",
      "Machine translation"
    ],
    "frontmatter": {
      "base_model": "Thermostatic/neuraltranslate-27b-mt-nah-es-v1.2",
      "datasets": [
        "Thermostatic/Axolotl-Spanish-Nahuatl-ShareGPT-Filtered-Splits"
      ],
      "language": [
        "es",
        "nah"
      ],
      "library_name": "transformers",
      "license": "mit",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "Translation",
        "Gemma 3",
        "Spanish",
        "Nahuatl",
        "Machine translation"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/Thermostatic/neuraltranslate-27b-mt-nah-es-v1.2  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-GGUF **This is a vision model - mmproj files (if any) will be in the static repository.**",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: Thermostatic/neuraltranslate-27b-mt-nah-es-v1.2\ndatasets:\n- Thermostatic/Axolotl-Spanish-Nahuatl-ShareGPT-Filtered-Splits\nlanguage:\n- es\n- nah\nlibrary_name: transformers\nlicense: mit\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- Translation\n- Gemma 3\n- Spanish\n- Nahuatl\n- Machine translation\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/Thermostatic/neuraltranslate-27b-mt-nah-es-v1.2\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#neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-GGUF\n\n**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-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/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ1_S.gguf) | i1-IQ1_S | 6.4 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ1_M.gguf) | i1-IQ1_M | 6.9 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ2_S.gguf) | i1-IQ2_S | 8.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ2_M.gguf) | i1-IQ2_M | 9.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 9.9 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q2_K.gguf) | i1-Q2_K | 10.6 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.8 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 11.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ3_S.gguf) | i1-IQ3_S | 12.3 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q4_0.gguf) | i1-Q4_0 | 15.7 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.6 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q4_1.gguf) | i1-Q4_1 | 17.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 18.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 19.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF/resolve/main/neuraltranslate-27b-mt-nah-es-v1.2.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | 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",
    "Translation",
    "Gemma 3",
    "Spanish",
    "Nahuatl",
    "Machine translation",
    "es",
    "nah",
    "dataset:Thermostatic/Axolotl-Spanish-Nahuatl-ShareGPT-Filtered-Splits",
    "base_model:Thermostatic/neuraltranslate-27b-mt-nah-es-v1.2",
    "base_model:quantized:Thermostatic/neuraltranslate-27b-mt-nah-es-v1.2",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 168,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-11T00:26:38.000Z",
  "created_at": "2025-06-26T10:43:33.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "685d2455406be5f132917174",
  "id": "mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF",
  "modelId": "mradermacher/neuraltranslate-27b-mt-nah-es-v1.2-i1-GGUF",
  "sha": "a2f30bff6a796aa45eb6aa36361e1bdcda581d0a",
  "createdAt": "2025-06-26T10:43:33.000Z",
  "lastModified": "2025-07-11T00:26:38.000Z",
  "author": "mradermacher",
  "downloads": 168,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}