I’ve spent the last months researching and building a dedicated inference workstation that can handle some serious local AI tasks. This is the second part in that series. The first article where I covered the hardware can be found here: Since I put together my local LLM inference rig with
The author details their journey of building a local inference workstation for AI tasks. They describe the hardware setup, including dual AMD AI Pro R9700 GPUs, and their experiences with various software and challenges faced during the process. The emphasis is on the value of local AI versus cloud services and the importance of blending both in practical applications.