soyaakinohara/gemma-4-31b-it-heretic-3.68bpw-14gb.gguf
Quantization (fewer layers) vs DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking. soyaakinohara/gemma-4-31b-it-heretic-3.68bpw-14gb.gguf matches part of DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking (772 of its 1188 tensors; the rest of DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking has no counterpart). On the shared part: soyaakinohara/gemma-4-31b-it-heretic-3.68bpw-14gb.gguf is a GGUF quantization (IQ2_S/Q4_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