GuYueshou/SenseNova-U1.5-8B-MoT-Q4_K_S-L0DownFix-GGUF
Quantization vs sensenova/SenseNova-U1.5-8B-MoT. GuYueshou/SenseNova-U1.5-8B-MoT-Q4_K_S-L0DownFix-GGUF is a GGUF quantization (Q4_K/F32) of the same weights: 525 tensors match exactly and 591 within quantization error.
Tensors changed: other 0/4, Embeddings 0/17, lm_head 0/1, Norms 0/506, MLP 0/252, Attention 0/336