Abiray/K2-Horizon-MoVA-36B-A4B-GGUF
Quantization vs IFM/K2-Horizon-MoVA-36B-A4B. Abiray/K2-Horizon-MoVA-36B-A4B-GGUF is a GGUF quantization (Q8_0) of the same weights: 123 tensors match exactly and 297 within quantization error.
Tensors changed: Norms 0/84, MLP 0/165, Attention 0/171