Add it to a GitHub README or profile β the card updates as the ranking changes:
DeepSeek V4 Flash 284B on AMD Strix Halo (gfx1151) β up to 32 tok/s decode & ~250 tok/s prefill via ROCmFPX, DSpark & ROCm 7.2
Heterogeneous Compute Cascade (HCC) β distributed 400B-parameter MoE inference across dual AMD Ryzen AI MAX+ 395 'Strix Halo' workstations via USB4.
Unlocking the power of the Halo NPU: NPU + iGPU live verification, compression, and routing research on AMD Strix Halo
Converter fixes, NVFP4 findings & Strix Halo ROCmFP4 benchmarks for NVIDIA Nemotron 3.5 Lightning 30B-A3B