iohann.s.titov@gmail.com Ivan S. Titov Converts the weights of a GGUF model file to Q4NX, the safetensors layout FastFlowLM loads on AMD Ryzen AI (XDNA2) NPUs. The converter repacks weights only. The NPU kernels are compiled per model and ship with FastFlowLM, so the source must be a fine-tune of a model that FastFlowLM already supports, with the same architecture and size. ROCm/FLM_Q4NX_Converter https://github.com/ROCm/FLM_Q4NX_Converter/issues