mradermacher/Calme-3.2-fp16-GGUF
Quantization vs Sakalti/Calme-3.2-fp16. mradermacher/Calme-3.2-fp16-GGUF is a GGUF quantization (IQ4_XS) of the same weights: 431 tensors match exactly and 604 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/173, MLP 0/258, Attention 0/602