axiomofmind/DeepSeek-V4-Flash-0731-NVFP4-GGUF
Not comparable yet vs axiomofmind/DeepSeek-V4-Flash-0731-NVFP4. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (88 of 138365/1586 match), usually an architecture llama.cpp's name map doesn't cover yet.