raulvidis/Ling-3.0-flash-ROCmFP4-STRIX-MTP-GGUF
Not comparable yet vs inclusionAI/Ling-3.0-flash. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (271 of 63783/938 match), usually an architecture llama.cpp's name map doesn't cover yet.