[jerrysievert]

> a random orange pi board with Qwen3-Coder-30B-A3B at Q3_K_XL (~12.9GB)

fantastic! what are you using to run it, llama.cpp? I have a few extra opi5's sitting around that would love some extra usage

[rao-v]

Yup! Build and ignore KleinAI and Vulkan etc. I’ve found that a clean CPU only build is optimal