GrahLnn/Hy-MT2-30B-A3B-4bit-GGUF
Quantization vs tencent/Hy-MT2-30B-A3B. GrahLnn/Hy-MT2-30B-A3B-4bit-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 240 tensors match exactly and 338 within quantization error.
Tensors changed: Norms 0/193, MLP 0/191, Attention 0/192, lm_head 0/1, Embeddings 0/1