mradermacher/MegaQwen-120B-GGUF
Quantization vs abideen/MegaQwen-120B. mradermacher/MegaQwen-120B-GGUF is a GGUF quantization (Q2_K) of the same weights: 702 tensors match exactly and 981 within quantization error.
Tensors changed: MLP 0/420, Attention 0/980, Embeddings 0/1, Norms 0/281, lm_head 0/1