jorge-erdb/Qwen3.6-35B-A3B-uncensored-heretic-GGUF
Abliterated vs Qwen/Qwen3.6-35B-A3B. jorge-erdb/Qwen3.6-35B-A3B-uncensored-heretic-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 32 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/101, MLP 30/160, Attention 10/40, lm_head 0/1