LiconStudio/Qwen3.5-27B-abliterated-GGUF
Abliterated vs Qwen/Qwen3.5-27B. LiconStudio/Qwen3.5-27B-abliterated-GGUF is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 52 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 52/192, Attention 8/64, Norms 0/161