divingclone/Hy-MT2-1.8B-NVFP4-Q4_K_M-GGUF
Quantization vs tencent/Hy-MT2-1.8B. divingclone/Hy-MT2-1.8B-NVFP4-Q4_K_M-GGUF is a GGUF quantization (Q4_K/Q6_K) of the same weights: 129 tensors match exactly and 81 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/32, Attention 0/48