mradermacher/Falcon2-5.5B-Polish-i1-GGUF
Quantization vs ssmits/Falcon2-5.5B-Polish. mradermacher/Falcon2-5.5B-Polish-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 58 tensors match exactly and 86 within quantization error.
Tensors changed: lm_head 0/1, Norms 0/58, MLP 0/56, Attention 0/28, Embeddings 0/1