mradermacher/cupidon-tiny-ro-i1-GGUF
Quantization vs BlackKakapo/cupidon-tiny-ro. mradermacher/cupidon-tiny-ro-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 24 tensors match exactly and 13 within quantization error.
Tensors changed: Embeddings 0/5, Norms 0/8, Attention 0/16, other 0/8