avar6/Hy4-Preview-gguf
Quantization vs tencent/Hy4-preview. avar6/Hy4-Preview-gguf is a GGUF quantization (IQ2_XS/IQ3_XXS) of the same weights: 454 tensors match exactly and 589 within quantization error.
Tensors changed: Embeddings 0/1, Attention 0/375, MLP 0/311, lm_head 0/1, Norms 0/355