mradermacher/alia-40b-instruct-2601-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "BSC-LT/ALIA-40b-instruct-2601",
    "datasets": [
      "CohereLabs/aya_dataset",
      "projecte-aina/CoQCat",
      "databricks/databricks-dolly-15k",
      "projecte-aina/dolly3k_ca",
      "projecte-aina/MentorES",
      "projecte-aina/MentorCA",
      "HuggingFaceH4/no_robots",
      "projecte-aina/RAG_Multilingual",
      "Unbabel/TowerBlocks-v0.2",
      "OpenAssistant/oasst2",
      "open-r1/OpenR1-Math-220k",
      "HuggingFaceFW/fineweb-edu",
      "allenai/WildChat-1M"
    ],
    "language": [
      "ca",
      "en",
      "es",
      "eu",
      "gl"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "frontmatter": {
      "base_model": "BSC-LT/ALIA-40b-instruct-2601",
      "datasets": [
        "CohereLabs/aya_dataset",
        "projecte-aina/CoQCat",
        "databricks/databricks-dolly-15k",
        "projecte-aina/dolly3k_ca",
        "projecte-aina/MentorES",
        "projecte-aina/MentorCA",
        "HuggingFaceH4/no_robots",
        "projecte-aina/RAG_Multilingual",
        "Unbabel/TowerBlocks-v0.2",
        "OpenAssistant/oasst2",
        "open-r1/OpenR1-Math-220k",
        "HuggingFaceFW/fineweb-edu",
        "allenai/WildChat-1M"
      ],
      "language": [
        "ca",
        "en",
        "es",
        "eu",
        "gl"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "mradermacher": [],
      "quantized_by": "mradermacher"
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/BSC-LT/ALIA-40b-instruct-2601  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: BSC-LT/ALIA-40b-instruct-2601\ndatasets:\n- CohereLabs/aya_dataset\n- projecte-aina/CoQCat\n- databricks/databricks-dolly-15k\n- projecte-aina/dolly3k_ca\n- projecte-aina/MentorES\n- projecte-aina/MentorCA\n- HuggingFaceH4/no_robots\n- projecte-aina/RAG_Multilingual\n- Unbabel/TowerBlocks-v0.2\n- OpenAssistant/oasst2\n- open-r1/OpenR1-Math-220k\n- HuggingFaceFW/fineweb-edu\n- allenai/WildChat-1M\nlanguage:\n- ca\n- en\n- es\n- eu\n- gl\nlibrary_name: transformers\nlicense: apache-2.0\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\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/BSC-LT/ALIA-40b-instruct-2601\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#ALIA-40b-instruct-2601-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-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/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ1_S.gguf) | i1-IQ1_S | 9.8 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ1_M.gguf) | i1-IQ1_M | 10.6 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 11.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ2_S.gguf) | i1-IQ2_S | 13.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ2_M.gguf) | i1-IQ2_M | 14.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q2_K_S.gguf) | i1-Q2_K_S | 14.8 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q2_K.gguf) | i1-Q2_K | 15.8 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 16.3 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ3_XS.gguf) | i1-IQ3_XS | 17.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.3 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ3_S.gguf) | i1-IQ3_S | 18.4 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ3_M.gguf) | i1-IQ3_M | 18.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q3_K_M.gguf) | i1-Q3_K_M | 20.1 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q3_K_L.gguf) | i1-Q3_K_L | 21.7 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-IQ4_XS.gguf) | i1-IQ4_XS | 22.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q4_0.gguf) | i1-Q4_0 | 23.5 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q4_K_S.gguf) | i1-Q4_K_S | 23.5 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q4_K_M.gguf) | i1-Q4_K_M | 24.7 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q4_1.gguf) | i1-Q4_1 | 25.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q5_K_S.gguf) | i1-Q5_K_S | 28.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q5_K_M.gguf) | i1-Q5_K_M | 28.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-i1-GGUF/resolve/main/ALIA-40b-instruct-2601.i1-Q6_K.gguf) | i1-Q6_K | 33.3 | 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",
    "ca",
    "en",
    "es",
    "eu",
    "gl",
    "dataset:CohereLabs/aya_dataset",
    "dataset:projecte-aina/CoQCat",
    "dataset:databricks/databricks-dolly-15k",
    "dataset:projecte-aina/dolly3k_ca",
    "dataset:projecte-aina/MentorES",
    "dataset:projecte-aina/MentorCA",
    "dataset:HuggingFaceH4/no_robots",
    "dataset:projecte-aina/RAG_Multilingual",
    "dataset:Unbabel/TowerBlocks-v0.2",
    "dataset:OpenAssistant/oasst2",
    "dataset:open-r1/OpenR1-Math-220k",
    "dataset:HuggingFaceFW/fineweb-edu",
    "dataset:allenai/WildChat-1M",
    "base_model:BSC-LT/ALIA-40b-instruct-2601",
    "base_model:quantized:BSC-LT/ALIA-40b-instruct-2601",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 627,
  "gated": false,
  "private": false,
  "last_modified": "2026-02-05T05:26:41.000Z",
  "created_at": "2026-02-03T08:28:20.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "6981b1a43c70281a3ae8a89e",
  "id": "mradermacher/ALIA-40b-instruct-2601-i1-GGUF",
  "modelId": "mradermacher/ALIA-40b-instruct-2601-i1-GGUF",
  "sha": "54864b37340b32337f7834a75b4068c9adef18c0",
  "createdAt": "2026-02-03T08:28:20.000Z",
  "lastModified": "2026-02-05T05:26:41.000Z",
  "author": "mradermacher",
  "downloads": 627,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}