ji-farthing/gemma-4-12B-it-MTP-ik-llama-GGUF
Quantization vs unsloth/gemma-4-12b-it-GGUF. ji-farthing/gemma-4-12B-it-MTP-ik-llama-GGUF is a GGUF quantization (Q8_0) of the same weights: 25 tensors match exactly and 21 within quantization error.
Tensors changed: other 0/5, Norms 0/21, MLP 0/12, Attention 0/8