mad-lab-ai/Qwen3.6-35B-A3B-tq-gguf
Full fine-tune vs Qwen/Qwen3.6-35B-A3B. mad-lab-ai/Qwen3.6-35B-A3B-tq-gguf is a GGUF (TQ1_0/Q6_K) of different weights. Fine-tune: 99% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 0/101, MLP 120/160, Attention 40/40, lm_head 1/1