How to Run this model at IQ1_S/IQ_M (plus IQ2s) and get decent performance

#1
by DavidAU - opened

I put together a quick how to, with three settings profiles (images) to get the most out of this model at IQ1_S / IQ1_M (as well as IQ2s) with a number of LLM/AI apps:

https://huggingface.co/DavidAU/Llama-3.3-70B-Instruct-How-To-Run-on-Low-BPW-IQ1_S-IQ1_M-at-maximum-speed-quality

Sign up or log in to comment