Hyphonical/gemma-4-E4B-it-Uncensored-MAX-opus-4.7-IQ4_XS-GGUF
Quantization (fewer layers) vs Hyphonical/gemma-4-E4B-it-Uncensored-MAX-opus-4.7. Hyphonical/gemma-4-E4B-it-Uncensored-MAX-opus-4.7-IQ4_XS-GGUF matches part of Hyphonical/gemma-4-E4B-it-Uncensored-MAX-opus-4.7 (677 of its 2130 tensors; the rest of Hyphonical/gemma-4-E4B-it-Uncensored-MAX-opus-4.7 has no counterpart). On the shared part: Hyphonical/gemma-4-E4B-it-Uncensored-MAX-opus-4.7-IQ4_XS-GGUF is a GGUF quantization (Q6_K/IQ4_XS) of the same weights: 297 tensors match exactly and 380 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168