ArtusDev/aquif-ai_aquif-3.5-Max-42B-A3B-EXL3

EXL3 quants of aquif-ai/aquif-3.5-Max-42B-A3B using exllamav3 for quantization.

Quants

Quant	BPW	Head Bits	Size (GB)
2.5_H6	2.5	6	14.14
3.0_H6	3.0	6	16.76
3.5_H6	3.5	6	19.36
4.0_H6	4.0	6	21.98
4.5_H6	4.5	6	24.57
5.0_H6	5.0	6	27.19
6.0_H6	6.0	6	32.41
8.0_H8	8.0	8	42.92

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 ArtusDev/aquif-ai_aquif-3.5-Max-42B-A3B-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.

See EXL community hub for request guidelines.

Made possible with cloud compute from lium.io

Downloads last month: -; Downloads are not tracked for this model. How to track