Add it to a GitHub README or profile β the card updates as the ranking changes:
CIRU llama.cpp runtime for Qwen3.8-Flash-CIRU-STRIX-IU4 on AMD Strix Halo
Qwen Image 2.1 Turbo Prediction and Strix Halo attention for ComfyUI
Fail-closed USB4 link qualification and paired Strix Halo model operations