mradermacher/gemma-portuguese-luana-2b-i1-GGUF
Quantization vs rhaymison/gemma-portuguese-luana-2b. mradermacher/gemma-portuguese-luana-2b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 37 tensors match exactly and 127 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 0/72