mradermacher/Falcon2-10B-multilingual-i1-GGUF
Quantization vs ssmits/Falcon2-8B-multilingual. mradermacher/Falcon2-10B-multilingual-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 88 tensors match exactly and 131 within quantization error.
Tensors changed: lm_head 0/1, Norms 0/88, MLP 0/86, Attention 0/43, Embeddings 0/1