JMingo/gemma-4-26B-A4B-it-qat-japanese-pruned-GGUF
Quantization vs JMingo/gemma-4-26B-A4B-it-qat-GGUF. JMingo/gemma-4-26B-A4B-it-qat-japanese-pruned-GGUF is a GGUF quantization (Q4_0) of the same weights: 332 tensors match exactly and 206 within quantization error.
Tensors changed: other 0/32, Norms 0/271, MLP 0/120, Attention 0/115