6block/Hy4-preview-GGUF
Quantization vs tencent/Hy4-preview. 6block/Hy4-preview-GGUF is a GGUF quantization (IQ4_XS) of the same weights: 453 tensors match exactly and 590 within quantization error.
Tensors changed: Embeddings 0/1, Attention 0/375, MLP 0/311, lm_head 0/1, Norms 0/355