My foray into local ai. Two BC-250 ex mining apus running Qwen3.6-35B-A3B Q4_K_M at 60 tok/s with 64k context

These boards cost me $115 each and I have them connected using llama.cpp with Vulkan and RPC on Bazzite. The boards have roughly 27GB of combined GPU memory and communicate over 1gb Ethernet. For around $300 including psu I’m loving the performance. I have a few more and want to see what 6 looks lik