mradermacher/llama-3.2-1b-4b-quad-moe-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "Fu01978/Llama-3.2-1B-4B-Quad-MoE",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "llama3.2",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "mixture-of-experts",
      "moe",
      "4-experts",
      "merge",
      "mergekit",
      "llama",
      "llama3.2"
    ],
    "frontmatter": {
      "base_model": "Fu01978/Llama-3.2-1B-4B-Quad-MoE",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "llama3.2",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "mixture-of-experts",
        "moe",
        "4-experts",
        "merge",
        "mergekit",
        "llama",
        "llama3.2"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/Fu01978/Llama-3.2-1B-4B-Quad-MoE  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: Fu01978/Llama-3.2-1B-4B-Quad-MoE\nlanguage:\n- en\nlibrary_name: transformers\nlicense: llama3.2\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- mixture-of-experts\n- moe\n- 4-experts\n- merge\n- mergekit\n- llama\n- llama3.2\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/Fu01978/Llama-3.2-1B-4B-Quad-MoE\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#Llama-3.2-1B-4B-Quad-MoE-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-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/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ1_M.gguf) | i1-IQ1_M | 1.1 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ2_M.gguf) | i1-IQ2_M | 1.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.5 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q2_K.gguf) | i1-Q2_K | 1.6 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.6 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.8 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ3_S.gguf) | i1-IQ3_S | 1.8 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ3_M.gguf) | i1-IQ3_M | 1.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.9 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.1 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.2 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q4_0.gguf) | i1-Q4_0 | 2.2 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.2 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.4 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q4_1.gguf) | i1-Q4_1 | 2.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF/resolve/main/Llama-3.2-1B-4B-Quad-MoE.i1-Q6_K.gguf) | i1-Q6_K | 3.1 | 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",
    "mixture-of-experts",
    "moe",
    "4-experts",
    "merge",
    "mergekit",
    "llama",
    "llama3.2",
    "en",
    "base_model:Fu01978/Llama-3.2-1B-4B-Quad-MoE",
    "base_model:quantized:Fu01978/Llama-3.2-1B-4B-Quad-MoE",
    "license:llama3.2",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 144,
  "gated": false,
  "private": false,
  "last_modified": "2026-02-13T13:51:26.000Z",
  "created_at": "2026-02-13T13:11:08.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "698f22ecbf4b552b05581ce6",
  "id": "mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF",
  "modelId": "mradermacher/Llama-3.2-1B-4B-Quad-MoE-i1-GGUF",
  "sha": "e10ff0968564738f8080c4a581391ec141f6fe38",
  "createdAt": "2026-02-13T13:11:08.000Z",
  "lastModified": "2026-02-13T13:51:26.000Z",
  "author": "mradermacher",
  "downloads": 144,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}