mradermacher/Hy-MT2-30B-A3B-GGUF
Quantization vs tencent/Hy-MT2-30B-A3B. mradermacher/Hy-MT2-30B-A3B-GGUF is a GGUF quantization (Q8_0) of the same weights: 246 tensors match exactly and 338 within quantization error.
Tensors changed: MLP 0/197, Norms 0/193, Attention 0/192, lm_head 0/1, Embeddings 0/1