satgeze/Hy3-1M-GGUF
Quantization vs tencent/Hy3. satgeze/Hy3-1M-GGUF is a GGUF quantization (IQ2_M) of the same weights: 402 tensors match exactly and 562 within quantization error.
Tensors changed: Attention 0/320, lm_head 0/1, MLP 0/321, Norms 0/321, Embeddings 0/1