GraySoft
Projects Models About FAQ Contact Download guIDE →

mradermacher/gpt-oss-20b-jail-broke-i1-gguf IQ3_S GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.

Model Intelligence Sheet

mradermacher/gpt-oss-20b-jail-broke-i1-gguf overview

About weighted/imatrix quants of https://huggingface.co/AIGym/gpt-oss-20B-jail-broke 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-20B-jail-broke-GGUF

transformersgguflanguage-modelcausal-lmgptred-teamingjailbreakevaluationenbase_model:AIGym/gpt-oss-20B-jail-brokebase_model:quantized:AIGym/gpt-oss-20B-jail-brokeendpoints_compatibleregion:usimatrixconversational
mradermacher/gpt-oss-20b-jail-broke-i1-gguf visual
Downloads
251
Likes
0
Pipeline
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

24 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
gpt-oss-20B-jail-broke.i1-IQ1_M.gguf GGUF IQ1_M 11.19 GB Download
gpt-oss-20B-jail-broke.i1-IQ1_S.gguf GGUF IQ1_S 11.19 GB Download
gpt-oss-20B-jail-broke.i1-IQ2_M.gguf GGUF IQ2_M 11.24 GB Download
gpt-oss-20B-jail-broke.i1-IQ2_S.gguf GGUF IQ2_S 11.24 GB Download
gpt-oss-20B-jail-broke.i1-IQ2_XS.gguf GGUF IQ2_XS 11.20 GB Download
gpt-oss-20B-jail-broke.i1-IQ2_XXS.gguf GGUF IQ2_XXS 11.19 GB Download
gpt-oss-20B-jail-broke.i1-IQ3_M.gguf GGUF IQ3_M 11.36 GB Download
gpt-oss-20B-jail-broke.i1-IQ3_S.gguf GGUF IQ3_S 11.24 GB Download
gpt-oss-20B-jail-broke.i1-IQ3_XS.gguf GGUF IQ3_XS 11.24 GB Download
gpt-oss-20B-jail-broke.i1-IQ3_XXS.gguf GGUF IQ3_XXS 11.24 GB Download
gpt-oss-20B-jail-broke.i1-IQ4_XS.gguf GGUF IQ4_XS 11.27 GB Download
gpt-oss-20B-jail-broke.i1-Q2_K.gguf GGUF Q2_K 11.24 GB Download
gpt-oss-20B-jail-broke.i1-Q2_K_S.gguf GGUF Q2_K_S 11.30 GB Download
gpt-oss-20B-jail-broke.i1-Q3_K_L.gguf GGUF Q3_K_L 12.42 GB Download
gpt-oss-20B-jail-broke.i1-Q3_K_M.gguf GGUF Q3_K_M 12.03 GB Download
gpt-oss-20B-jail-broke.i1-Q3_K_S.gguf GGUF Q3_K_S 11.23 GB Download
gpt-oss-20B-jail-broke.i1-Q4_0.gguf GGUF 11.31 GB Download
gpt-oss-20B-jail-broke.i1-Q4_1.gguf GGUF 12.45 GB Download
gpt-oss-20B-jail-broke.i1-Q4_K_M.gguf GGUF Q4_K_M 14.72 GB Download
gpt-oss-20B-jail-broke.i1-Q4_K_S.gguf GGUF Q4_K_S 13.65 GB Download
gpt-oss-20B-jail-broke.i1-Q5_K_M.gguf GGUF Q5_K_M 15.73 GB Download
gpt-oss-20B-jail-broke.i1-Q5_K_S.gguf GGUF Q5_K_S 14.80 GB Download
gpt-oss-20B-jail-broke.i1-Q6_K.gguf GGUF Q6_K 20.67 GB Download
gpt-oss-20B-jail-broke.imatrix.gguf GGUF 26.78 MB Download

Model Details Live

Model Slug
mradermacher/gpt-oss-20b-jail-broke-i1-gguf
Author
mradermacher
Pipeline Task
Library
transformers
Created
2025-08-17
Last Modified
2025-12-09
Gated
No
Private
No
HF SHA
0990a822b6ec358bf5ed81342d38425e4bae431a
License
Unknown
Language
en
Base Model
AIGym/gpt-oss-20B-jail-broke

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "AIGym/gpt-oss-20B-jail-broke",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "language-model",
      "causal-lm",
      "gpt",
      "red-teaming",
      "jailbreak",
      "evaluation"
    ],
    "frontmatter": {
      "base_model": "AIGym/gpt-oss-20B-jail-broke",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "language-model",
        "causal-lm",
        "gpt",
        "red-teaming",
        "jailbreak",
        "evaluation"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/AIGym/gpt-oss-20B-jail-broke  ***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-20B-jail-broke-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: AIGym/gpt-oss-20B-jail-broke\nlanguage:\n- en\nlibrary_name: transformers\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- language-model\n- causal-lm\n- gpt\n- red-teaming\n- jailbreak\n- evaluation\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/AIGym/gpt-oss-20B-jail-broke\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-20B-jail-broke-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-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-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ1_S.gguf) | i1-IQ1_S | 12.1 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.2 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ2_S.gguf) | i1-IQ2_S | 12.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ3_S.gguf) | i1-IQ3_S | 12.2 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q4_0.gguf) | i1-Q4_0 | 12.2 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.4 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q4_1.gguf) | i1-Q4_1 | 13.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20B-jail-broke-i1-GGUF/resolve/main/gpt-oss-20B-jail-broke.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",
    "language-model",
    "causal-lm",
    "gpt",
    "red-teaming",
    "jailbreak",
    "evaluation",
    "en",
    "base_model:AIGym/gpt-oss-20B-jail-broke",
    "base_model:quantized:AIGym/gpt-oss-20B-jail-broke",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 251,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-09T03:13:24.000Z",
  "created_at": "2025-08-17T01:05:38.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "68a12ae2e6cf989ff0fa28e4",
  "id": "mradermacher/gpt-oss-20B-jail-broke-i1-GGUF",
  "modelId": "mradermacher/gpt-oss-20B-jail-broke-i1-GGUF",
  "sha": "0990a822b6ec358bf5ed81342d38425e4bae431a",
  "createdAt": "2025-08-17T01:05:38.000Z",
  "lastModified": "2025-12-09T03:13:24.000Z",
  "author": "mradermacher",
  "downloads": 251,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}