mradermacher/gpt-oss-sanguine-20b-v1-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "paperboygold/gpt-oss-sanguine-20b-v1",
    "datasets": [
      "NousResearch/Hermes-3-Dataset",
      "Anthropic/hh-rlhf",
      "teknium/OpenHermes-2.5",
      "microsoft/orca-math-word-problems-200k",
      "WizardLM/WizardLM_evol_instruct_V2_196k",
      "calme/legalkit",
      "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
      "Yoondi/bluemoon-roleplay-chat-jsonl",
      "LooksJuicy/Chinese-Roleplay-Novel",
      "zhouzr/pk-roleplay",
      "openerotica/long-roleplay-v0.1",
      "mrcuddle/nous-character-codex",
      "Arasaaf/myuri_roleplay",
      "AlekseyKorshuk/gpt-roleplay-realm-chatml",
      "diwank/gpt_roleplay_realm-chatml",
      "Gryphe/Sonnet3.5-Charcard-Roleplay",
      "hieunguyenminh/roleplay",
      "zerofata/Roleplay-Anime-Characters",
      "Locutusque/FalseReject-sharegpt",
      "QuixiAI/open-instruct-uncensored",
      "allenai/WildChat-4.8M-Full",
      "nvidia/Llama-Nemotron-Post-Training-Dataset",
      "WizardLMTeam/WizardLM_evol_instruct_V2_196k",
      "nvidia/OpenCodeReasoning",
      "MaziyarPanahi/calme-legalkit-v0.2",
      "Nitral-AI/Cybersecurity-ShareGPT",
      "savaniDhruv/Cybersecurity_Attack_Dataset",
      "openerotica/erotica-analysis",
      "demelin/moral_stories"
    ],
    "language": [
      "en",
      "zh"
    ],
    "library_name": "transformers",
    "license": "mit",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "peft",
      "lora",
      "roleplay",
      "creative-writing",
      "consequence-based-alignment",
      "gpt-oss",
      "openai-harmony"
    ],
    "frontmatter": {
      "base_model": "paperboygold/gpt-oss-sanguine-20b-v1",
      "datasets": [
        "NousResearch/Hermes-3-Dataset",
        "Anthropic/hh-rlhf",
        "teknium/OpenHermes-2.5",
        "microsoft/orca-math-word-problems-200k",
        "WizardLM/WizardLM_evol_instruct_V2_196k",
        "calme/legalkit",
        "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
        "Yoondi/bluemoon-roleplay-chat-jsonl",
        "LooksJuicy/Chinese-Roleplay-Novel",
        "zhouzr/pk-roleplay",
        "openerotica/long-roleplay-v0.1",
        "mrcuddle/nous-character-codex",
        "Arasaaf/myuri_roleplay",
        "AlekseyKorshuk/gpt-roleplay-realm-chatml",
        "diwank/gpt_roleplay_realm-chatml",
        "Gryphe/Sonnet3.5-Charcard-Roleplay",
        "hieunguyenminh/roleplay",
        "zerofata/Roleplay-Anime-Characters",
        "Locutusque/FalseReject-sharegpt",
        "QuixiAI/open-instruct-uncensored",
        "allenai/WildChat-4.8M-Full",
        "nvidia/Llama-Nemotron-Post-Training-Dataset",
        "WizardLMTeam/WizardLM_evol_instruct_V2_196k",
        "nvidia/OpenCodeReasoning",
        "MaziyarPanahi/calme-legalkit-v0.2",
        "Nitral-AI/Cybersecurity-ShareGPT",
        "savaniDhruv/Cybersecurity_Attack_Dataset",
        "openerotica/erotica-analysis",
        "demelin/moral_stories"
      ],
      "language": [
        "en",
        "zh"
      ],
      "library_name": "transformers",
      "license": "mit",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "peft",
        "lora",
        "roleplay",
        "creative-writing",
        "consequence-based-alignment",
        "gpt-oss",
        "openai-harmony"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/paperboygold/gpt-oss-sanguine-20b-v1  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: paperboygold/gpt-oss-sanguine-20b-v1\ndatasets:\n- NousResearch/Hermes-3-Dataset\n- Anthropic/hh-rlhf\n- teknium/OpenHermes-2.5\n- microsoft/orca-math-word-problems-200k\n- WizardLM/WizardLM_evol_instruct_V2_196k\n- calme/legalkit\n- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF\n- Yoondi/bluemoon-roleplay-chat-jsonl\n- LooksJuicy/Chinese-Roleplay-Novel\n- zhouzr/pk-roleplay\n- openerotica/long-roleplay-v0.1\n- mrcuddle/nous-character-codex\n- Arasaaf/myuri_roleplay\n- AlekseyKorshuk/gpt-roleplay-realm-chatml\n- diwank/gpt_roleplay_realm-chatml\n- Gryphe/Sonnet3.5-Charcard-Roleplay\n- hieunguyenminh/roleplay\n- zerofata/Roleplay-Anime-Characters\n- Locutusque/FalseReject-sharegpt\n- QuixiAI/open-instruct-uncensored\n- allenai/WildChat-4.8M-Full\n- nvidia/Llama-Nemotron-Post-Training-Dataset\n- WizardLMTeam/WizardLM_evol_instruct_V2_196k\n- nvidia/OpenCodeReasoning\n- MaziyarPanahi/calme-legalkit-v0.2\n- Nitral-AI/Cybersecurity-ShareGPT\n- savaniDhruv/Cybersecurity_Attack_Dataset\n- openerotica/erotica-analysis\n- demelin/moral_stories\nlanguage:\n- en\n- zh\nlibrary_name: transformers\nlicense: mit\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- peft\n- lora\n- roleplay\n- creative-writing\n- consequence-based-alignment\n- gpt-oss\n- openai-harmony\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/paperboygold/gpt-oss-sanguine-20b-v1\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#gpt-oss-sanguine-20b-v1-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-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/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 12.1 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.2 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 12.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 12.2 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q4_0.gguf) | i1-Q4_0 | 12.2 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.4 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q4_1.gguf) | i1-Q4_1 | 13.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF/resolve/main/gpt-oss-sanguine-20b-v1.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | 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",
    "peft",
    "lora",
    "roleplay",
    "creative-writing",
    "consequence-based-alignment",
    "gpt-oss",
    "openai-harmony",
    "en",
    "zh",
    "dataset:NousResearch/Hermes-3-Dataset",
    "dataset:Anthropic/hh-rlhf",
    "dataset:teknium/OpenHermes-2.5",
    "dataset:microsoft/orca-math-word-problems-200k",
    "dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
    "dataset:calme/legalkit",
    "dataset:nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
    "dataset:Yoondi/bluemoon-roleplay-chat-jsonl",
    "dataset:LooksJuicy/Chinese-Roleplay-Novel",
    "dataset:zhouzr/pk-roleplay",
    "dataset:openerotica/long-roleplay-v0.1",
    "dataset:mrcuddle/nous-character-codex",
    "dataset:Arasaaf/myuri_roleplay",
    "dataset:AlekseyKorshuk/gpt-roleplay-realm-chatml",
    "dataset:diwank/gpt_roleplay_realm-chatml",
    "dataset:Gryphe/Sonnet3.5-Charcard-Roleplay",
    "dataset:hieunguyenminh/roleplay",
    "dataset:zerofata/Roleplay-Anime-Characters",
    "dataset:Locutusque/FalseReject-sharegpt",
    "dataset:QuixiAI/open-instruct-uncensored",
    "dataset:allenai/WildChat-4.8M-Full",
    "dataset:nvidia/Llama-Nemotron-Post-Training-Dataset",
    "dataset:WizardLMTeam/WizardLM_evol_instruct_V2_196k",
    "dataset:nvidia/OpenCodeReasoning",
    "dataset:MaziyarPanahi/calme-legalkit-v0.2",
    "dataset:Nitral-AI/Cybersecurity-ShareGPT",
    "dataset:savaniDhruv/Cybersecurity_Attack_Dataset",
    "dataset:openerotica/erotica-analysis",
    "dataset:demelin/moral_stories",
    "base_model:paperboygold/gpt-oss-sanguine-20b-v1",
    "base_model:adapter:paperboygold/gpt-oss-sanguine-20b-v1",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 753,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-16T03:02:17.000Z",
  "created_at": "2025-08-19T19:32:19.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "68a4d143963641acb2ddd864",
  "id": "mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF",
  "modelId": "mradermacher/gpt-oss-sanguine-20b-v1-i1-GGUF",
  "sha": "5e8964e58805ed1160a9bd8b35081fe068fb0bd7",
  "createdAt": "2025-08-19T19:32:19.000Z",
  "lastModified": "2025-12-16T03:02:17.000Z",
  "author": "mradermacher",
  "downloads": 753,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}