bartowski/Hy3-GGUF
Quantization vs tencent/Hy3. bartowski/Hy3-GGUF is a GGUF quantization (Q8_0) of the same weights: 409 tensors match exactly and 570 within quantization error.
Tensors changed: Attention 0/324, lm_head 0/1, MLP 0/325, other 0/1, Norms 0/327, Embeddings 0/1