---
base_model: Delta-Vector/Austral-32B-GLM4-Winton
base_model_relation: quantized
quantized_by: ArtusDev
license: apache-2.0
language:
- en
library_name: transformers
tags:
- roleplay
- finetune
- axolotl
- adventure
- creative-writing
- GLM4
- 32B
- exl3
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
---

## EXL3 Quants of Delta-Vector/Austral-32B-GLM4-Winton

EXL3 quants of [Delta-Vector/Austral-32B-GLM4-Winton](https://huggingface.co/Delta-Vector/Austral-32B-GLM4-Winton) using <a href="https://github.com/turboderp-org/exllamav3/">exllamav3</a> for quantization.

### Quants
| Quant(Revision) | Bits per Weight | Head Bits |
| -------- | ---------- | --------- |
| [2.5_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-32B-GLM4-Winton-EXL3/tree/2.5bpw_H6) | 2.5 | 6 |
| [3.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-32B-GLM4-Winton-EXL3/tree/3.0bpw_H6) | 3.0 | 6 |
| [3.5_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-32B-GLM4-Winton-EXL3/tree/3.5bpw_H6) | 3.5 | 6 |
| [4.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-32B-GLM4-Winton-EXL3/tree/4.0bpw_H6) | 4.0 | 6 |
| [4.5_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-32B-GLM4-Winton-EXL3/tree/4.5bpw_H6) | 4.5 | 6 |
| [5.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-32B-GLM4-Winton-EXL3/tree/5.0bpw_H6) | 5.0 | 6 |
| [6.0_H6](https://huggingface.co/ArtusDev/Delta-Vector_Austral-32B-GLM4-Winton-EXL3/tree/6.0bpw_H6) | 6.0 | 6 |
| [8.0_H8](https://huggingface.co/ArtusDev/Delta-Vector_Austral-32B-GLM4-Winton-EXL3/tree/8.0bpw_H8) | 8.0 | 8 |

### Downloading quants with huggingface-cli

<details>
  <summary>Click to view download instructions</summary>

Install hugginface-cli:

```bash
pip install -U "huggingface_hub[cli]"
```

Download quant by targeting the specific quant revision (branch):

```
huggingface-cli download ArtusDev/Delta-Vector_Austral-32B-GLM4-Winton-EXL3 --revision "5.0bpw_H6" --local-dir ./
```
</details>