metadata
base_model: fedric95/Qwen3-4B-Instruct-2507-unc
base_model_relation: quantized
quantized_by: ArtusDev
license: apache-2.0
pipeline_tag: text-generation
tags:
- exl3
ArtusDev/fedric95_Qwen3-4B-Instruct-2507-unc-EXL3
EXL3 quants of fedric95/Qwen3-4B-Instruct-2507-unc using exllamav3 for quantization.
Quants
| Quant | BPW | Head Bits | Size (GB) |
|---|---|---|---|
| 2.5_H6 | 2.5 | 6 | 2.23 |
| 3.0_H6 | 3.0 | 6 | 2.45 |
| 3.5_H6 | 3.5 | 6 | 2.68 |
| 4.0_H6 | 4.0 | 6 | 2.91 |
| 4.5_H6 | 4.5 | 6 | 3.13 |
| 5.0_H6 | 5.0 | 6 | 3.36 |
| 6.0_H6 | 6.0 | 6 | 3.82 |
| 8.0_H8 | 8.0 | 8 | 4.82 |
How to Download and Use Quants
You can download quants by targeting specific size using the Hugging Face CLI.
Click for download commands
1. Install huggingface-cli:
pip install -U "huggingface_hub[cli]"huggingface-cli download ArtusDev/fedric95_Qwen3-4B-Instruct-2507-unc-EXL3 --revision "5.0bpw_H6" --local-dir ./EXL3 quants can be run with any inference client that supports EXL3, such as TabbyAPI. Refer to documentation for set up instructions.
Acknowledgements
Made possible with cloud compute from lium.io