Nvidia has published a competitive llama3-70B QA/RAG fine tune

Lest any need ask "Where GGUF?":

https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF

Looking at the table comparison I almost closed the tab until I realized the 70b model was at the last column

ChatGPT ₥ price has to come down ASAP.