---
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
---
## About

<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type:  -->
<!-- ### tags:  -->
static quants of https://huggingface.co/Delta-Vector/Austral-32B-GLM4-Winton

<!-- provided-files -->

***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Austral-32B-GLM4-Winton-GGUF).***

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-i1-GGUF
## Usage

If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.

## Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q2_K.gguf) | Q2_K | 12.4 |  |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q3_K_S.gguf) | Q3_K_S | 14.5 |  |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q3_K_M.gguf) | Q3_K_M | 16.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q3_K_L.gguf) | Q3_K_L | 17.3 |  |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.IQ4_XS.gguf) | IQ4_XS | 17.9 |  |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q4_K_S.gguf) | Q4_K_S | 18.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q4_K_M.gguf) | Q4_K_M | 19.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q5_K_S.gguf) | Q5_K_S | 22.6 |  |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q5_K_M.gguf) | Q5_K_M | 23.2 |  |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q6_K.gguf) | Q6_K | 26.8 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Austral-32B-GLM4-Winton-GGUF/resolve/main/Austral-32B-GLM4-Winton.Q8_0.gguf) | Q8_0 | 34.7 | fast, best quality |

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

## FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

## Thanks

I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

<!-- end -->