sleepyeldrazi/DeepSeek-v4-Flash-REAP-K128-NVFP4
Not comparable yet vs deepseek-ai/DeepSeek-V4-Flash. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (1 of 69187/1414 match), usually an architecture llama.cpp's name map doesn't cover yet.