LeadFootThrottleCock/Qwen3-VL-8B-Thinking-heretic-GGUF
Abliterated (fewer layers) vs Qwen/Qwen3-VL-8B-Thinking. LeadFootThrottleCock/Qwen3-VL-8B-Thinking-heretic-GGUF matches part of Qwen/Qwen3-VL-8B-Thinking (397 of its 750 tensors; the rest of Qwen/Qwen3-VL-8B-Thinking has no counterpart). On the shared part: LeadFootThrottleCock/Qwen3-VL-8B-Thinking-heretic-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 30 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/145, MLP 29/108, Attention 30/144