wepiqx/gemma-4-12B-it-SHQ6-GGUF
Quantization vs google/gemma-4-12B-it-qat-q4_0-unquantized. wepiqx/gemma-4-12B-it-SHQ6-GGUF is a GGUF quantization (IQ4_XS) of the same weights: 289 tensors match exactly and 329 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/184