---
license: llama3
---
[exllamav2](https://github.com/turboderp/exllamav2) quant for fixed version of [mattshumer/Reflection-Llama-3.1-70B](https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B)
Runs smoothly on 2x3090 with 48GB VRAM
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel: