mradermacher/qwen3-14b-cobalt2-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "ValiantLabs/Qwen3-14B-Cobalt2",
    "datasets": [
      "zwhe99/DeepMath-103K",
      "sequelbox/Raiden-DeepSeek-R1"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "cobalt",
      "cobalt-2",
      "valiant",
      "valiant-labs",
      "qwen",
      "qwen-3",
      "qwen-3-14b",
      "14b",
      "math",
      "math-reasoning",
      "math-instruct",
      "reasoning",
      "problem-solving",
      "creative",
      "analytical",
      "expert",
      "rationality",
      "conversational",
      "chat",
      "instruct"
    ],
    "frontmatter": {
      "base_model": "ValiantLabs/Qwen3-14B-Cobalt2",
      "datasets": [
        "zwhe99/DeepMath-103K",
        "sequelbox/Raiden-DeepSeek-R1"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "cobalt",
        "cobalt-2",
        "valiant",
        "valiant-labs",
        "qwen",
        "qwen-3",
        "qwen-3-14b",
        "14b",
        "math",
        "math-reasoning",
        "math-instruct",
        "reasoning",
        "problem-solving",
        "creative",
        "analytical",
        "expert",
        "rationality",
        "conversational",
        "chat",
        "instruct"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/ValiantLabs/Qwen3-14B-Cobalt2  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: ValiantLabs/Qwen3-14B-Cobalt2\ndatasets:\n- zwhe99/DeepMath-103K\n- sequelbox/Raiden-DeepSeek-R1\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- cobalt\n- cobalt-2\n- valiant\n- valiant-labs\n- qwen\n- qwen-3\n- qwen-3-14b\n- 14b\n- math\n- math-reasoning\n- math-instruct\n- reasoning\n- problem-solving\n- creative\n- analytical\n- expert\n- rationality\n- conversational\n- chat\n- instruct\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/ValiantLabs/Qwen3-14B-Cobalt2\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#Qwen3-14B-Cobalt2-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-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/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ1_M.gguf) | i1-IQ1_M | 3.9 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ2_M.gguf) | i1-IQ2_M | 5.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-Cobalt2-i1-GGUF/resolve/main/Qwen3-14B-Cobalt2.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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",
    "cobalt",
    "cobalt-2",
    "valiant",
    "valiant-labs",
    "qwen",
    "qwen-3",
    "qwen-3-14b",
    "14b",
    "math",
    "math-reasoning",
    "math-instruct",
    "reasoning",
    "problem-solving",
    "creative",
    "analytical",
    "expert",
    "rationality",
    "conversational",
    "chat",
    "instruct",
    "en",
    "dataset:zwhe99/DeepMath-103K",
    "dataset:sequelbox/Raiden-DeepSeek-R1",
    "base_model:ValiantLabs/Qwen3-14B-Cobalt2",
    "base_model:quantized:ValiantLabs/Qwen3-14B-Cobalt2",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix"
  ],
  "likes": 1,
  "downloads": 506,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-11T02:32:35.000Z",
  "created_at": "2025-05-21T16:50:54.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "682e046e685400151104ef50",
  "id": "mradermacher/Qwen3-14B-Cobalt2-i1-GGUF",
  "modelId": "mradermacher/Qwen3-14B-Cobalt2-i1-GGUF",
  "sha": "7f393692e0c3b6a06d1e16b38ba2e56770564215",
  "createdAt": "2025-05-21T16:50:54.000Z",
  "lastModified": "2025-07-11T02:32:35.000Z",
  "author": "mradermacher",
  "downloads": 506,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}