--- base_model: Tarek07/Aurora-Borealis-LLaMa-70B base_model_relation: quantized quantized_by: ArtusDev library_name: transformers tags: - mergekit - merge - exl3 license: llama3.3 --- ## EXL3 Quants of Tarek07/Aurora-Borealis-LLaMa-70B EXL3 quants of [Tarek07/Aurora-Borealis-LLaMa-70B](https://huggingface.co/Tarek07/Aurora-Borealis-LLaMa-70B) using exllamav3 for quantization. ### Quants | Quant(Revision) | Bits per Weight | Head Bits | | -------- | ---------- | --------- | | [2.5_H6](https://huggingface.co/ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3/tree/2.5bpw_H6) | 2.5 | 6 | | [3.0_H6](https://huggingface.co/ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3/tree/3.0bpw_H6) | 3.0 | 6 | | [3.5_H6](https://huggingface.co/ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3/tree/3.5bpw_H6) | 3.5 | 6 | | [4.0_H6](https://huggingface.co/ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3/tree/4.0bpw_H6) | 4.0 | 6 | | [4.25_H6](https://huggingface.co/ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3/tree/4.25bpw_H6) | 4.25 | 6 | | [5.0_H6](https://huggingface.co/ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3/tree/5.0bpw_H6) | 5.0 | 6 | | [6.0_H6](https://huggingface.co/ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3/tree/6.0bpw_H6) | 6.0 | 6 | | [8.0_H6](https://huggingface.co/ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3/tree/8.0bpw_H6) | 8.0 | 6 | | [8.0_H8](https://huggingface.co/ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3/tree/8.0bpw_H8) | 8.0 | 8 | ### Downloading quants with huggingface-cli
Click to view download instructions Install hugginface-cli: ```bash pip install -U "huggingface_hub[cli]" ``` Download quant by targeting the specific quant revision (branch): ``` huggingface-cli download ArtusDev/Tarek07_Aurora-Borealis-LLaMa-70B-EXL3 --revision "5bpw_H6" --local-dir ./ ```