mradermacher/deepseek-moe-16b-base-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "deepseek-ai/deepseek-moe-16b-base",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://github.com/deepseek-ai/DeepSeek-MoE/blob/main/LICENSE-MODEL",
    "license_name": "deepseek",
    "quantized_by": "mradermacher",
    "frontmatter": {
      "base_model": "deepseek-ai/deepseek-moe-16b-base",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "other",
      "license_link": "https://github.com/deepseek-ai/DeepSeek-MoE/blob/main/LICENSE-MODEL",
      "license_name": "deepseek",
      "quantized_by": "mradermacher"
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      static quants of https://huggingface.co/deepseek-ai/deepseek-moe-16b-base  weighted/imatrix quants are available at https://huggingface.co/mradermacher/deepseek-moe-16b-base-i1-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: deepseek-ai/deepseek-moe-16b-base\nlanguage:\n- en\nlibrary_name: transformers\nlicense: other\nlicense_link: https://github.com/deepseek-ai/DeepSeek-MoE/blob/main/LICENSE-MODEL\nlicense_name: deepseek\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:  -->\nstatic quants of https://huggingface.co/deepseek-ai/deepseek-moe-16b-base\n\n<!-- provided-files -->\nweighted/imatrix quants are available at https://huggingface.co/mradermacher/deepseek-moe-16b-base-i1-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/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q2_K.gguf) | Q2_K | 6.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q3_K_S.gguf) | Q3_K_S | 7.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q3_K_M.gguf) | Q3_K_M | 8.6 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q3_K_L.gguf) | Q3_K_L | 8.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.IQ4_XS.gguf) | IQ4_XS | 9.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q4_K_S.gguf) | Q4_K_S | 10.0 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q4_K_M.gguf) | Q4_K_M | 11.0 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q5_K_S.gguf) | Q5_K_S | 11.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q5_K_M.gguf) | Q5_K_M | 12.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q6_K.gguf) | Q6_K | 14.8 | very good quality |\n| [GGUF](https://huggingface.co/mradermacher/deepseek-moe-16b-base-GGUF/resolve/main/deepseek-moe-16b-base.Q8_0.gguf) | Q8_0 | 17.5 | fast, best quality |\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.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "en",
    "base_model:deepseek-ai/deepseek-moe-16b-base",
    "base_model:quantized:deepseek-ai/deepseek-moe-16b-base",
    "license:other",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 186,
  "gated": false,
  "private": false,
  "last_modified": "2025-02-08T08:58:41.000Z",
  "created_at": "2025-02-08T04:28:21.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "67a6dd65f73abd3d814ba361",
  "id": "mradermacher/deepseek-moe-16b-base-GGUF",
  "modelId": "mradermacher/deepseek-moe-16b-base-GGUF",
  "sha": "14f74fbbd63a5610fbb714b1d6d959a495c50054",
  "createdAt": "2025-02-08T04:28:21.000Z",
  "lastModified": "2025-02-08T08:58:41.000Z",
  "author": "mradermacher",
  "downloads": 186,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 13
}