mradermacher/deepthought-moe-8x3b-r1-llama-3.2-reasoning-18b-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "DavidAU/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "quantized_by": "mradermacher",
    "tags": [
      "Llama 3.2",
      "8 X 3B",
      "128k context",
      "moe",
      "8 experts",
      "reasoning",
      "thinking",
      "r1",
      "cot",
      "deepseek",
      "mixture of experts",
      "mergekit",
      "merge",
      "llama-3",
      "llama-3.2"
    ],
    "frontmatter": {
      "base_model": "DavidAU/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "quantized_by": "mradermacher",
      "tags": [
        "Llama 3.2",
        "8 X 3B",
        "128k context",
        "moe",
        "8 experts",
        "reasoning",
        "thinking",
        "r1",
        "cot",
        "deepseek",
        "mixture of experts",
        "mergekit",
        "merge",
        "llama-3",
        "llama-3.2"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/DavidAU/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B  static quants are available at https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: DavidAU/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B\nlanguage:\n- en\nlibrary_name: transformers\nquantized_by: mradermacher\ntags:\n- Llama 3.2\n- 8 X 3B\n- 128k context\n- moe\n- 8 experts\n- reasoning\n- thinking\n- r1\n- cot\n- deepseek\n- mixture of experts\n- mergekit\n- merge\n- llama-3\n- llama-3.2\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/DavidAU/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-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/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ1_S.gguf) | i1-IQ1_S | 4.2 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.6 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ2_S.gguf) | i1-IQ2_S | 5.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ2_M.gguf) | i1-IQ2_M | 6.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 6.6 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q2_K.gguf) | i1-Q2_K | 7.1 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.5 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 7.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ3_S.gguf) | i1-IQ3_S | 8.4 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.4 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ3_M.gguf) | i1-IQ3_M | 8.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.1 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 9.7 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 10.7 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q4_0.gguf) | i1-Q4_0 | 10.7 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 10.8 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 11.4 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q4_1.gguf) | i1-Q4_1 | 11.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 12.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 13.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF/resolve/main/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B.i1-Q6_K.gguf) | i1-Q6_K | 15.3 | 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",
    "Llama 3.2",
    "8 X 3B",
    "128k context",
    "moe",
    "8 experts",
    "reasoning",
    "thinking",
    "r1",
    "cot",
    "deepseek",
    "mixture of experts",
    "mergekit",
    "merge",
    "llama-3",
    "llama-3.2",
    "en",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 428,
  "gated": false,
  "private": false,
  "last_modified": "2025-05-28T19:49:32.000Z",
  "created_at": "2025-02-21T17:25:25.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "67b8b7055d22156c27c32637",
  "id": "mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF",
  "modelId": "mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-GGUF",
  "sha": "b6eed88dc479e799af6c774fb122ab33cab166b3",
  "createdAt": "2025-02-21T17:25:25.000Z",
  "lastModified": "2025-05-28T19:49:32.000Z",
  "author": "mradermacher",
  "downloads": 428,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}