mradermacher/atom-80b-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "vanta-research/atom-80b",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "qwen3",
      "qwen3-next",
      "qwen",
      "vanta-research",
      "cognitive-configuration",
      "text-generation",
      "instruction-following",
      "cognitive-ai",
      "large-language-model",
      "helpful-ai",
      "aligned-ai",
      "philosophical",
      "emotional-intelligence",
      "atom",
      "collaborative-ai",
      "collaboration",
      "conversational",
      "conversational-ai",
      "alignment-ai",
      "chat",
      "chatbot",
      "reasoning",
      "friendly",
      "ai-research",
      "ai-alignment-research",
      "ai-alignment",
      "ai-behavior-research",
      "ai-collaboration-research"
    ],
    "frontmatter": {
      "base_model": "vanta-research/atom-80b",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "qwen3",
        "qwen3-next",
        "qwen",
        "vanta-research",
        "cognitive-configuration",
        "text-generation",
        "instruction-following",
        "cognitive-ai",
        "large-language-model",
        "helpful-ai",
        "aligned-ai",
        "philosophical",
        "emotional-intelligence",
        "atom",
        "collaborative-ai",
        "collaboration",
        "conversational",
        "conversational-ai",
        "alignment-ai",
        "chat",
        "chatbot",
        "reasoning",
        "friendly",
        "ai-research",
        "ai-alignment-research",
        "ai-alignment",
        "ai-behavior-research",
        "ai-collaboration-research"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/vanta-research/atom-80b  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/atom-80b-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: vanta-research/atom-80b\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- qwen3\n- qwen3-next\n- qwen\n- vanta-research\n- cognitive-configuration\n- text-generation\n- instruction-following\n- cognitive-ai\n- large-language-model\n- helpful-ai\n- aligned-ai\n- philosophical\n- emotional-intelligence\n- atom\n- collaborative-ai\n- collaboration\n- conversational\n- conversational-ai\n- alignment-ai\n- chat\n- chatbot\n- reasoning\n- friendly\n- ai-research\n- ai-alignment-research\n- ai-alignment\n- ai-behavior-research\n- ai-collaboration-research\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/vanta-research/atom-80b\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#atom-80b-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/atom-80b-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/atom-80b-i1-GGUF/resolve/main/atom-80b.imatrix.gguf) | imatrix | 0.6 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ1_S.gguf) | i1-IQ1_S | 16.3 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ1_M.gguf) | i1-IQ1_M | 18.1 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 21.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 23.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ2_S.gguf) | i1-IQ2_S | 23.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ2_M.gguf) | i1-IQ2_M | 26.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 27.4 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q2_K.gguf) | i1-Q2_K | 29.2 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 30.9 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 32.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 34.6 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ3_S.gguf) | i1-IQ3_S | 34.6 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ3_M.gguf) | i1-IQ3_M | 35.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 38.3 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 41.3 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 42.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q4_0.gguf) | i1-Q4_0 | 45.4 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 45.6 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 48.5 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q4_1.gguf) | i1-Q4_1 | 50.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 55.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 56.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/atom-80b-i1-GGUF/resolve/main/atom-80b.i1-Q6_K.gguf) | i1-Q6_K | 65.6 | 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",
    "qwen3",
    "qwen3-next",
    "qwen",
    "vanta-research",
    "cognitive-configuration",
    "text-generation",
    "instruction-following",
    "cognitive-ai",
    "large-language-model",
    "helpful-ai",
    "aligned-ai",
    "philosophical",
    "emotional-intelligence",
    "atom",
    "collaborative-ai",
    "collaboration",
    "conversational",
    "conversational-ai",
    "alignment-ai",
    "chat",
    "chatbot",
    "reasoning",
    "friendly",
    "ai-research",
    "ai-alignment-research",
    "ai-alignment",
    "ai-behavior-research",
    "ai-collaboration-research",
    "en",
    "base_model:vanta-research/atom-80b",
    "base_model:quantized:vanta-research/atom-80b",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix"
  ],
  "likes": 3,
  "downloads": 247,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-02T21:05:24.000Z",
  "created_at": "2026-01-06T13:27:19.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "695d0db7d58c0fd587427150",
  "id": "mradermacher/atom-80b-i1-GGUF",
  "modelId": "mradermacher/atom-80b-i1-GGUF",
  "sha": "9baedcb2da28e6bf6e477168b12e7eb4bacb28f0",
  "createdAt": "2026-01-06T13:27:19.000Z",
  "lastModified": "2026-03-02T21:05:24.000Z",
  "author": "mradermacher",
  "downloads": 247,
  "likes": 3,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 26
}