hoidhxd/SenseNova-U1.5-8B-GGUF-v2
Quantization vs sensenova/SenseNova-U1.5-8B-MoT-Preview. hoidhxd/SenseNova-U1.5-8B-GGUF-v2 is a GGUF quantization (Q4_0/F16) of the same weights: 527 tensors match exactly and 589 within quantization error.
Tensors changed: Embeddings 0/17, other 0/4, Norms 0/506, MLP 0/252, Attention 0/336, lm_head 0/1