Janvitos/gemma-4-12B-it-qat-assistant-MTP-Q8_0-GGUF
Quantization vs google/gemma-4-12B-it-qat-q4_0-unquantized-assistant. Janvitos/gemma-4-12B-it-qat-assistant-MTP-Q8_0-GGUF is a GGUF quantization (Q8_0) of the same weights: 21 tensors match exactly and 23 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/21, MLP 0/12, Attention 0/8, other 0/2