mradermacher/Aira-2-portuguese-560M-i1-GGUF
Quantization vs nicholasKluge/Aira-2-portuguese-560M. mradermacher/Aira-2-portuguese-560M-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 170 tensors match exactly and 73 within quantization error.
Tensors changed: Norms 0/98, MLP 0/96, Attention 0/48, Embeddings 0/1