sudo apt-get install wget gawk gcc g++ make cmake automake curl unzip zip bzip2 tar gzip pigz parallel build-essential libncurses5-dev libc6-dev zlib1g zlib1g-dev libtbb-dev libtbb2 python python-dev ...

So far, running LLMs has required a large amount of computing resources, mainly GPUs. Running locally, a simple prompt with a typical LLM takes on an average Mac ...