timfromhcs/Gemma-4-E4B-it-qat-q4_0-unquantized-abliterated-GGUF
Abliterated (fewer layers) vs google/gemma-4-E4B-it-qat-q4_0-unquantized. timfromhcs/Gemma-4-E4B-it-qat-q4_0-unquantized-abliterated-GGUF matches part of google/gemma-4-E4B-it-qat-q4_0-unquantized (623 of its 2076 tensors; the rest of google/gemma-4-E4B-it-qat-q4_0-unquantized has no counterpart). On the shared part: timfromhcs/Gemma-4-E4B-it-qat-q4_0-unquantized-abliterated-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 42 of 42 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/2, Norms 0/278, MLP 42/126, other 0/85, Attention 42/132