GraySoft
Projects Models About FAQ Contact Download guIDE →

mradermacher/dolphin3.0-llama3.1-1b-abliterated-i1-gguf IQ3_XS 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/dolphin3.0-llama3.1-1b-abliterated-i1-gguf overview

About weighted/imatrix quants of https://huggingface.co/Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated static quants are available at https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-GGUF

transformersggufenbase_model:Nexesenex/Dolphin3.0-Llama3.1-1B-abliteratedbase_model:quantized:Nexesenex/Dolphin3.0-Llama3.1-1B-abliteratedlicense:llama3.1endpoints_compatibleregion:usimatrixconversational
mradermacher/dolphin3.0-llama3.1-1b-abliterated-i1-gguf visual
Downloads
98
Likes
0
Pipeline
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

24 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ1_M.gguf GGUF IQ1_M 394.45 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ1_S.gguf GGUF IQ1_S 375.32 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ2_M.gguf GGUF IQ2_M 491.57 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ2_S.gguf GGUF IQ2_S 466.07 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ2_XS.gguf GGUF IQ2_XS 453.82 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ2_XXS.gguf GGUF IQ2_XXS 426.32 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ3_M.gguf GGUF IQ3_M 626.84 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ3_S.gguf GGUF IQ3_S 614.09 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ3_XS.gguf GGUF IQ3_XS 592.34 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ3_XXS.gguf GGUF IQ3_XXS 536.07 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ4_NL.gguf GGUF IQ4_NL 737.22 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ4_XS.gguf GGUF IQ4_XS 708.72 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q2_K.gguf GGUF Q2_K 553.97 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q2_K_S.gguf GGUF Q2_K_S 528.97 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q3_K_L.gguf GGUF Q3_K_L 698.59 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q3_K_M.gguf GGUF Q3_K_M 658.84 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q3_K_S.gguf GGUF Q3_K_S 611.97 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q4_0.gguf GGUF 737.22 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q4_1.gguf GGUF 793.22 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q4_K_M.gguf GGUF Q4_K_M 770.28 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q4_K_S.gguf GGUF Q4_K_S 739.72 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q5_K_M.gguf GGUF Q5_K_M 869.28 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q5_K_S.gguf GGUF Q5_K_S 851.22 MB Download
Dolphin3.0-Llama3.1-1B-abliterated.i1-Q6_K.gguf GGUF Q6_K 974.47 MB Download

Model Details Live

Model Slug
mradermacher/dolphin3.0-llama3.1-1b-abliterated-i1-gguf
Author
mradermacher
Pipeline Task
Library
transformers
Created
2025-03-01
Last Modified
2025-03-01
Gated
No
Private
No
HF SHA
db927c2e4943b20c421c95edc233e1f20d7f6d96
License
llama3.1
Language
en
Base Model
Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "llama3.1",
    "quantized_by": "mradermacher",
    "frontmatter": {
      "base_model": "Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "llama3.1",
      "quantized_by": "mradermacher"
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated  static quants are available at https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated\nlanguage:\n- en\nlibrary_name: transformers\nlicense: llama3.1\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: nicoboss -->\nweighted/imatrix quants of https://huggingface.co/Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-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/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.8 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.9 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.9 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q4_1.gguf) | i1-Q4_1 | 0.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF/resolve/main/Dolphin3.0-Llama3.1-1B-abliterated.i1-Q6_K.gguf) | i1-Q6_K | 1.1 | 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",
    "en",
    "base_model:Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated",
    "base_model:quantized:Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated",
    "license:llama3.1",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 98,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-01T10:25:18.000Z",
  "created_at": "2025-03-01T10:03:25.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "67c2db6d5c1ed1f81015db9f",
  "id": "mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF",
  "modelId": "mradermacher/Dolphin3.0-Llama3.1-1B-abliterated-i1-GGUF",
  "sha": "db927c2e4943b20c421c95edc233e1f20d7f6d96",
  "createdAt": "2025-03-01T10:03:25.000Z",
  "lastModified": "2025-03-01T10:25:18.000Z",
  "author": "mradermacher",
  "downloads": 98,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}