NeuralDreamer/gemma-4-31B-it-heretic-i1-GGUF_ND
Quantization (fewer layers) vs coder3101/gemma-4-31B-it-heretic. NeuralDreamer/gemma-4-31B-it-heretic-i1-GGUF_ND matches part of coder3101/gemma-4-31B-it-heretic (772 of its 1188 tensors; the rest of coder3101/gemma-4-31B-it-heretic has no counterpart). On the shared part: NeuralDreamer/gemma-4-31B-it-heretic-i1-GGUF_ND is a GGUF quantization (Q6_K) 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