llmfan46/gemma-4-31B-it-qat-q4_0-uncensored-heretic-GGUF
Quantization (fewer layers) vs llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic. llmfan46/gemma-4-31B-it-qat-q4_0-uncensored-heretic-GGUF matches part of llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic (772 of its 1188 tensors; the rest of llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic has no counterpart). On the shared part: llmfan46/gemma-4-31B-it-qat-q4_0-uncensored-heretic-GGUF is a GGUF quantization (Q4_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