hyperspaceai/diffusiongemma-26B-A4B-asym-2bitexp-GGUF
Quantization vs unsloth/diffusiongemma-26B-A4B-it-GGUF. hyperspaceai/diffusiongemma-26B-A4B-asym-2bitexp-GGUF is a GGUF quantization (IQ2_S/IQ4_NL) of the same weights: 423 tensors match exactly and 269 within quantization error.
Tensors changed: other 0/65, MLP 0/240, Norms 0/272, Attention 0/115