tensorblock/katanemo_Arch-Router-1.5B-GGUF
Quantization vs katanemo/Arch-Router-1.5B. tensorblock/katanemo_Arch-Router-1.5B-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 141 tensors match exactly and 197 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196