Hacker News Reader

> It's certainly not on a level with ChatGPT, but what is?

how can we load this 4bit GPU Version: https://huggingface.co/TheBloke/guanaco-65B-GPTQas that is in safetensors format

How much ram/vram required?

At least 48GB of RAM to run with llama.cpp, which now has CUDA GPU Offloading support.

The more you can fit on your GPU (in VRAM) the better (for speed), but no GPU is strictly required.