ressl/gemma-4-31B-it-uncensored-GGUF
Quantization (fewer layers) vs ressl/gemma-4-31B-it-uncensored. ressl/gemma-4-31B-it-uncensored-GGUF matches part of ressl/gemma-4-31B-it-uncensored (772 of its 1188 tensors; the rest of ressl/gemma-4-31B-it-uncensored has no counterpart). On the shared part: ressl/gemma-4-31B-it-uncensored-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 411 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230