pfeifferj/DeepSeek-V4.1-Flash-GSQ-RCO-GGUF
Not comparable yet vs deepseek-ai/DeepSeek-V4.1-Flash. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (82 of 96085/1047 match), usually an architecture llama.cpp's name map doesn't cover yet.