Add it to a GitHub README or profile β the card updates as the ranking changes:
Local AI coding agent harness for AMD Strix Halo (Ryzen AI Max+ 395): Qwen3.8 125B on the iGPU, NPU side-jobs, crash recovery, logged benchmarks. Works with any OpenAI-compatible engine; cloud optional.
playtest-graded benchmark for local LLM stacks: a 10-file game build, 19 static checks, a runtime soak, and a human playing it