AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF
Quantization vs AesSedai/MiMo-V2.6-Flash-MOPD-GGUF. AMAImedia/MiMo-V2.6-Flash-MOPD-BPW2.5-GGUF is a GGUF quantization (IQ2_XXS/IQ3_XXS) of the same weights: 380 tensors match exactly and 128 within quantization error.
Tensors changed: lm_head 0/1, Norms 0/112, other 0/51, Attention 0/144, MLP 0/200