I want to host some LLM’s locally and use more advanced models. Since new hardware is out of the question, I think I should be able to pull something off buying some yesteryear equipment on ebay etc. Did anybody attempt such a project? Does it scale horizontally? (I.e. can I connext two boxes to overcome single box slowness?)
2010 is ancient technology, according to wikipedia Nvidia released the 600 series in 2012… Even if there was some inference engine supporting it then lack of computational speed and memory bandwidth would probably make it not worth the effort.