Loke-60000/DeepSeek-V4-Flash-Vision-Exp-Abliterated-EXL3-K2.2-D2
Not comparable yet vs apetersson/DeepSeek-V4-Flash-Vision-Exp-Abliterated. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (88 of 1371/143289 match), usually an architecture llama.cpp's name map doesn't cover yet.