allura-quants/allura-org_Luna-27B-v0-EXL3
EXL3 quants of allura-org/Luna-27B-v0 using exllamav3 for quantization.
Quants
| Quant | BPW | Head Bits | Size (GB) |
|---|---|---|---|
| 2.5_H6 | 2.5 | 6 | 12.78 |
| 3.0_H6 | 3.0 | 6 | 14.38 |
| 3.5_H6 | 3.5 | 6 | 15.98 |
| 4.0_H6 | 4.0 | 6 | 17.58 |
| 4.5_H6 | 4.5 | 6 | 19.18 |
| 5.0_H6 | 5.0 | 6 | 20.78 |
| 6.0_H6 | 6.0 | 6 | 23.98 |
| 8.0_H8 | 8.0 | 8 | 30.73 |
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]"
2. Download a specific quant:
huggingface-cli download allura-quants/allura-org_Luna-27B-v0-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.