HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP
Full fine-tune vs google/gemma-4-26B-A4B-it. HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, Norms 199/271, MLP 90/90, other 30/30, Attention 115/115
1 derivatives checked
- satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF: Same weights, repacked