nightmedia/Qwen3.6-35B-A3B-Brainwaves-Nex-Uncensored
Full fine-tune vs AllSpark-Research/Iris-mini. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 5/5, Norms 247/247, Attention 392/392, MLP 397/1165, lm_head 1/1, other 1/1