mradermacher/DeepSeek-V4-Flash-0731-Abliterated-FP8-i1-GGUF
Not comparable yet vs apetersson/DeepSeek-V4-Flash-0731-Abliterated-FP8. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 72317/1536 match), usually an architecture llama.cpp's name map doesn't cover yet.