jfiekdjdk/gemma-4-31b-it-heretic-ara-gguf
Quantization (fewer layers) vs trohrbaugh/gemma-4-31b-it-heretic-ara. jfiekdjdk/gemma-4-31b-it-heretic-ara-gguf matches part of trohrbaugh/gemma-4-31b-it-heretic-ara (772 of its 1188 tensors; the rest of trohrbaugh/gemma-4-31b-it-heretic-ara has no counterpart). On the shared part: jfiekdjdk/gemma-4-31b-it-heretic-ara-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