GraySoft
Projects Models About FAQ Contact Download guIDE →

mradermacher/austral-32b-glm4-winton-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/austral-32b-glm4-winton-i1-gguf overview

About weighted/imatrix quants of https://huggingface.co/Delta-Vector/Austral-32B-GLM4-Winton For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF

transformersggufroleplayfinetuneaxolotladventurecreative-writingGLM432Bendataset:Delta-Vector/Tauri-Rep-Remover-KTOdataset:Delta-Vector/Orion-LN-V1-ShareGPTdataset:Delta-Vector/Orion-Personamaxx-RPdataset:Delta-Vector/Orion-Co-Writer-51Kdataset:Delta-Vector/Orion-Praxis-Co-Writerdataset:Delta-Vector/Orion-Shoujo-AI-Filtered-ShareGPTdataset:Delta-Vector/Orion-PIPPA-Cleaned-V2dataset:Delta-Vector/Orion-Alpindale-LN-ShareGPTdataset:Delta-Vector/Orion-Deepseek-V3-RP-Filtereddataset:Delta-Vector/Orion-Books-V2-ShareGPTdataset:Delta-Vector/Orion-Light-Novels-Roleplay-Logs-Books-Oh-My-duplicate-turns-removeddataset:Delta-Vector/Orion-RP-Guilddataset:Delta-Vector/Orion-Creative_Writing-Complexitydataset:Delta-Vector/Orion-Deepseek-R1-RP-Filtereddataset:Delta-Vector/Orion-Storium-Prefixed-Cleandataset:Delta-Vector/Orion-Misc-Sharegpt-Prefixeddataset:Delta-Vector/Orion-LIMARP-Complexitydataset:Delta-Vector/Orion-BlueSky-10K-Complexitydataset:Delta-Vector/Orion-OpenCAI-ShareGPTdataset:Delta-Vector/Orion-Roleplay-Logs-Sharegpt-Ngram-cleaned
mradermacher/austral-32b-glm4-winton-i1-gguf visual
Downloads
145
Likes
2
Pipeline
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

23 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Austral-32B-GLM4-Winton.i1-IQ1_M.gguf GGUF IQ1_M 7.36 GB Download
Austral-32B-GLM4-Winton.i1-IQ1_S.gguf GGUF IQ1_S 6.77 GB Download
Austral-32B-GLM4-Winton.i1-IQ2_M.gguf GGUF IQ2_M 10.50 GB Download
Austral-32B-GLM4-Winton.i1-IQ2_S.gguf GGUF IQ2_S 9.70 GB Download
Austral-32B-GLM4-Winton.i1-IQ2_XS.gguf GGUF IQ2_XS 9.22 GB Download
Austral-32B-GLM4-Winton.i1-IQ2_XXS.gguf GGUF IQ2_XXS 8.36 GB Download
Austral-32B-GLM4-Winton.i1-IQ3_M.gguf GGUF IQ3_M 13.80 GB Download
Austral-32B-GLM4-Winton.i1-IQ3_S.gguf GGUF IQ3_S 13.40 GB Download
Austral-32B-GLM4-Winton.i1-IQ3_XS.gguf GGUF IQ3_XS 12.72 GB Download
Austral-32B-GLM4-Winton.i1-IQ3_XXS.gguf GGUF IQ3_XXS 11.90 GB Download
Austral-32B-GLM4-Winton.i1-IQ4_XS.gguf GGUF IQ4_XS 16.39 GB Download
Austral-32B-GLM4-Winton.i1-Q2_K.gguf GGUF Q2_K 11.45 GB Download
Austral-32B-GLM4-Winton.i1-Q2_K_S.gguf GGUF Q2_K_S 10.63 GB Download
Austral-32B-GLM4-Winton.i1-Q3_K_L.gguf GGUF Q3_K_L 16.03 GB Download
Austral-32B-GLM4-Winton.i1-Q3_K_M.gguf GGUF Q3_K_M 14.80 GB Download
Austral-32B-GLM4-Winton.i1-Q3_K_S.gguf GGUF Q3_K_S 13.38 GB Download
Austral-32B-GLM4-Winton.i1-Q4_0.gguf GGUF 17.35 GB Download
Austral-32B-GLM4-Winton.i1-Q4_1.gguf GGUF 19.14 GB Download
Austral-32B-GLM4-Winton.i1-Q4_K_M.gguf GGUF Q4_K_M 18.33 GB Download
Austral-32B-GLM4-Winton.i1-Q4_K_S.gguf GGUF Q4_K_S 17.41 GB Download
Austral-32B-GLM4-Winton.i1-Q5_K_M.gguf GGUF Q5_K_M 21.51 GB Download
Austral-32B-GLM4-Winton.i1-Q5_K_S.gguf GGUF Q5_K_S 20.98 GB Download
Austral-32B-GLM4-Winton.i1-Q6_K.gguf GGUF Q6_K 24.89 GB Download

Model Details Live

Model Slug
mradermacher/austral-32b-glm4-winton-i1-gguf
Author
mradermacher
Pipeline Task
Library
transformers
Created
2025-07-21
Last Modified
2025-07-22
Gated
No
Private
No
HF SHA
9d6eefd95c09cad6363236d174361fff021b48e8
License
apache-2.0
Language
en
Base Model
Delta-Vector/Austral-32B-GLM4-Winton

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "Delta-Vector/Austral-32B-GLM4-Winton",
    "datasets": [
      "Delta-Vector/Tauri-Rep-Remover-KTO",
      "Delta-Vector/Orion-LN-V1-ShareGPT",
      "Delta-Vector/Orion-Personamaxx-RP",
      "Delta-Vector/Orion-Co-Writer-51K",
      "Delta-Vector/Orion-Praxis-Co-Writer",
      "Delta-Vector/Orion-Shoujo-AI-Filtered-ShareGPT",
      "Delta-Vector/Orion-PIPPA-Cleaned-V2",
      "Delta-Vector/Orion-Alpindale-LN-ShareGPT",
      "Delta-Vector/Orion-Deepseek-V3-RP-Filtered",
      "Delta-Vector/Orion-Books-V2-ShareGPT",
      "Delta-Vector/Orion-Light-Novels-Roleplay-Logs-Books-Oh-My-duplicate-turns-removed",
      "Delta-Vector/Orion-RP-Guild",
      "Delta-Vector/Orion-Creative_Writing-Complexity",
      "Delta-Vector/Orion-Deepseek-R1-RP-Filtered",
      "Delta-Vector/Orion-Storium-Prefixed-Clean",
      "Delta-Vector/Orion-Misc-Sharegpt-Prefixed",
      "Delta-Vector/Orion-LIMARP-Complexity",
      "Delta-Vector/Orion-BlueSky-10K-Complexity",
      "Delta-Vector/Orion-OpenCAI-ShareGPT",
      "Delta-Vector/Orion-Roleplay-Logs-Sharegpt-Ngram-cleaned",
      "Delta-Vector/Orion-vanilla-backrooms-claude-sharegpt"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "roleplay",
      "finetune",
      "axolotl",
      "adventure",
      "creative-writing",
      "GLM4",
      "32B"
    ],
    "frontmatter": {
      "base_model": "Delta-Vector/Austral-32B-GLM4-Winton",
      "datasets": [
        "Delta-Vector/Tauri-Rep-Remover-KTO",
        "Delta-Vector/Orion-LN-V1-ShareGPT",
        "Delta-Vector/Orion-Personamaxx-RP",
        "Delta-Vector/Orion-Co-Writer-51K",
        "Delta-Vector/Orion-Praxis-Co-Writer",
        "Delta-Vector/Orion-Shoujo-AI-Filtered-ShareGPT",
        "Delta-Vector/Orion-PIPPA-Cleaned-V2",
        "Delta-Vector/Orion-Alpindale-LN-ShareGPT",
        "Delta-Vector/Orion-Deepseek-V3-RP-Filtered",
        "Delta-Vector/Orion-Books-V2-ShareGPT",
        "Delta-Vector/Orion-Light-Novels-Roleplay-Logs-Books-Oh-My-duplicate-turns-removed",
        "Delta-Vector/Orion-RP-Guild",
        "Delta-Vector/Orion-Creative_Writing-Complexity",
        "Delta-Vector/Orion-Deepseek-R1-RP-Filtered",
        "Delta-Vector/Orion-Storium-Prefixed-Clean",
        "Delta-Vector/Orion-Misc-Sharegpt-Prefixed",
        "Delta-Vector/Orion-LIMARP-Complexity",
        "Delta-Vector/Orion-BlueSky-10K-Complexity",
        "Delta-Vector/Orion-OpenCAI-ShareGPT",
        "Delta-Vector/Orion-Roleplay-Logs-Sharegpt-Ngram-cleaned",
        "Delta-Vector/Orion-vanilla-backrooms-claude-sharegpt"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "roleplay",
        "finetune",
        "axolotl",
        "adventure",
        "creative-writing",
        "GLM4",
        "32B"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/Delta-Vector/Austral-32B-GLM4-Winton  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: Delta-Vector/Austral-32B-GLM4-Winton\ndatasets:\n- Delta-Vector/Tauri-Rep-Remover-KTO\n- Delta-Vector/Orion-LN-V1-ShareGPT\n- Delta-Vector/Orion-Personamaxx-RP\n- Delta-Vector/Orion-Co-Writer-51K\n- Delta-Vector/Orion-Praxis-Co-Writer\n- Delta-Vector/Orion-Shoujo-AI-Filtered-ShareGPT\n- Delta-Vector/Orion-PIPPA-Cleaned-V2\n- Delta-Vector/Orion-Alpindale-LN-ShareGPT\n- Delta-Vector/Orion-Deepseek-V3-RP-Filtered\n- Delta-Vector/Orion-Books-V2-ShareGPT\n- Delta-Vector/Orion-Light-Novels-Roleplay-Logs-Books-Oh-My-duplicate-turns-removed\n- Delta-Vector/Orion-RP-Guild\n- Delta-Vector/Orion-Creative_Writing-Complexity\n- Delta-Vector/Orion-Deepseek-R1-RP-Filtered\n- Delta-Vector/Orion-Storium-Prefixed-Clean\n- Delta-Vector/Orion-Misc-Sharegpt-Prefixed\n- Delta-Vector/Orion-LIMARP-Complexity\n- Delta-Vector/Orion-BlueSky-10K-Complexity\n- Delta-Vector/Orion-OpenCAI-ShareGPT\n- Delta-Vector/Orion-Roleplay-Logs-Sharegpt-Ngram-cleaned\n- Delta-Vector/Orion-vanilla-backrooms-claude-sharegpt\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- roleplay\n- finetune\n- axolotl\n- adventure\n- creative-writing\n- GLM4\n- 32B\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/Delta-Vector/Austral-32B-GLM4-Winton\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#Austral-32B-GLM4-Winton-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-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/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.5 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q4_0.gguf) | i1-Q4_0 | 18.7 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.8 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.8 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q4_1.gguf) | i1-Q4_1 | 20.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF/resolve/main/Austral-32B-GLM4-Winton.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | 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",
    "roleplay",
    "finetune",
    "axolotl",
    "adventure",
    "creative-writing",
    "GLM4",
    "32B",
    "en",
    "dataset:Delta-Vector/Tauri-Rep-Remover-KTO",
    "dataset:Delta-Vector/Orion-LN-V1-ShareGPT",
    "dataset:Delta-Vector/Orion-Personamaxx-RP",
    "dataset:Delta-Vector/Orion-Co-Writer-51K",
    "dataset:Delta-Vector/Orion-Praxis-Co-Writer",
    "dataset:Delta-Vector/Orion-Shoujo-AI-Filtered-ShareGPT",
    "dataset:Delta-Vector/Orion-PIPPA-Cleaned-V2",
    "dataset:Delta-Vector/Orion-Alpindale-LN-ShareGPT",
    "dataset:Delta-Vector/Orion-Deepseek-V3-RP-Filtered",
    "dataset:Delta-Vector/Orion-Books-V2-ShareGPT",
    "dataset:Delta-Vector/Orion-Light-Novels-Roleplay-Logs-Books-Oh-My-duplicate-turns-removed",
    "dataset:Delta-Vector/Orion-RP-Guild",
    "dataset:Delta-Vector/Orion-Creative_Writing-Complexity",
    "dataset:Delta-Vector/Orion-Deepseek-R1-RP-Filtered",
    "dataset:Delta-Vector/Orion-Storium-Prefixed-Clean",
    "dataset:Delta-Vector/Orion-Misc-Sharegpt-Prefixed",
    "dataset:Delta-Vector/Orion-LIMARP-Complexity",
    "dataset:Delta-Vector/Orion-BlueSky-10K-Complexity",
    "dataset:Delta-Vector/Orion-OpenCAI-ShareGPT",
    "dataset:Delta-Vector/Orion-Roleplay-Logs-Sharegpt-Ngram-cleaned",
    "dataset:Delta-Vector/Orion-vanilla-backrooms-claude-sharegpt",
    "base_model:Delta-Vector/Austral-32B-GLM4-Winton",
    "base_model:quantized:Delta-Vector/Austral-32B-GLM4-Winton",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 2,
  "downloads": 145,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-22T05:36:50.000Z",
  "created_at": "2025-07-21T15:57:38.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "687e63721179958929f59f6a",
  "id": "mradermacher/Austral-32B-GLM4-Winton-i1-GGUF",
  "modelId": "mradermacher/Austral-32B-GLM4-Winton-i1-GGUF",
  "sha": "9d6eefd95c09cad6363236d174361fff021b48e8",
  "createdAt": "2025-07-21T15:57:38.000Z",
  "lastModified": "2025-07-22T05:36:50.000Z",
  "author": "mradermacher",
  "downloads": 145,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}