realrebelai/SenseNova-U1.5-8B_GGUFs
Quantization vs sensenova/SenseNova-U1.5-8B-MoT. realrebelai/SenseNova-U1.5-8B_GGUFs is a GGUF quantization (Q8_0) of the same weights: 524 tensors match exactly and 592 within quantization error.
Tensors changed: other 0/4, Embeddings 0/17, lm_head 0/1, Norms 0/506, MLP 0/252, Attention 0/336