---
license: llama3
library_name: transformers
---

# Description

This is a 4-bit GPTQ quantized model of [failspy/Meta-Llama-3-8B-Instruct-abliterated-v3](https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3)
It is quantized with `wikitext2` dataset.
Its file size is 5.73 GB, and can fit into a 8GB VRAM GPU.