|
|
--- |
|
|
base_model: mistralai/Mistral-Small-3.2-24B-Instruct-2506 |
|
|
base_model_relation: quantized |
|
|
quantized_by: ArtusDev |
|
|
language: |
|
|
- en |
|
|
- fr |
|
|
- de |
|
|
- es |
|
|
- pt |
|
|
- it |
|
|
- ja |
|
|
- ko |
|
|
- ru |
|
|
- zh |
|
|
- ar |
|
|
- fa |
|
|
- id |
|
|
- ms |
|
|
- ne |
|
|
- pl |
|
|
- ro |
|
|
- sr |
|
|
- sv |
|
|
- tr |
|
|
- uk |
|
|
- vi |
|
|
- hi |
|
|
- bn |
|
|
license: apache-2.0 |
|
|
pipeline_tag: image-text-to-text |
|
|
tags: |
|
|
- exl3 |
|
|
--- |
|
|
|
|
|
## EXL3 Quants of mistralai/Mistral-Small-3.2-24B-Instruct-2506 |
|
|
|
|
|
EXL3 quants of [mistralai/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506) using <a href="https://github.com/turboderp-org/exllamav3/">exllamav3</a> for quantization. |
|
|
|
|
|
Based on the HF conversion of the base 3.2 model by unsloth: [unsloth/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506) |
|
|
|
|
|
### Quants |
|
|
| Quant(Revision) | Bits per Weight | Head Bits | |
|
|
| -------- | ---------- | --------- | |
|
|
| [2.0_H6](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/2.0bpw_H6) | 2.0 | 6 | |
|
|
| [2.5_H6](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/2.5bpw_H6) | 2.5 | 6 | |
|
|
| [3.0_H6](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/3.0bpw_H6) | 3.0 | 6 | |
|
|
| [3.5_H6](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/3.5bpw_H6) | 3.5 | 6 | |
|
|
| [4.0_H6](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/4.0bpw_H6) | 4.0 | 6 | |
|
|
| [4.5_H6](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/4.5bpw_H6) | 4.5 | 6 | |
|
|
| [5.0_H6](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/5.0bpw_H6) | 5.0 | 6 | |
|
|
| [5.5_H8](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/5.5bpw_H8) | 5.5 | 8 | |
|
|
| [6.0_H6](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/6.0bpw_H6) | 6.0 | 6 | |
|
|
| [8.0_H6](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3/tree/8.0bpw_H6) | 8.0 | 6 | |
|
|
| [8.0_H8](https://huggingface.co/ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-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/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3 --revision "5.0bpw_H6" --local-dir ./ |
|
|
``` |
|
|
</details> |
