Strix Halo (8060S / gfx1151), Qwen-3.8-27B @ Q8 and Q6 UD v3, up to 256K ctx, llama.cpp, DFlash2, vision, real workloads quality and steady performances, optimized recipes, ...

英文标题：Strix Halo (8060S / gfx1151), Qwen-3.8-27B @ Q8 and Q6 UD v3, up to 256K ctx, llama.cpp, DFlash2, vision, real workloads quality and steady performances, optimized recipes, ...

Hi fellows fully-local halos, after manually following existing guides, I decided to build an LLM API endpoint installation and optimization guide that works even when autonomously followed by my pi agent, so I can install/experiment/reinstall easily and without babysitting. Q8 is my default citize