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?)
I’m running Qwen 3.6 35B A3B (the MoE model) on an 8GB Vram Nvidia GPU with 32 GB of ram, with tweaking (and Turboquant) I’ve got it up to 30-40 Tokens per second and a 260k Context. It’s very usable. I’ve seen people report success with Dual 3060 Cards, but you’re still talking $1000-1500 for that kind of setup even if you have parts of it already.