HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP
Full fine-tune (fewer layers) vs google/gemma-4-31B-it. HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP matches part of google/gemma-4-31B-it (772 of its 1188 tensors; the rest of google/gemma-4-31B-it has no counterpart). On the shared part: HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 1/1, Norms 210/361, MLP 180/180, Attention 230/230
3 derivatives checked
- fallentree/Gemma4-31B-Uncensored-GP100-GGUF: Quantization
- satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF: Same weights, repacked
- BahamutRU/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF: Same weights, repacked