williamliao/gemma-4-26B-A4B-it-DFlash-GGUF
Same weights, converted vs z-lab/gemma-4-26B-A4B-it-DFlash. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: other 0/1, Norms 0/21, MLP 0/15, Attention 0/20
Same weights, converted vs z-lab/gemma-4-26B-A4B-it-DFlash. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: other 0/1, Norms 0/21, MLP 0/15, Attention 0/20