mradermacher/Llama3-18B-lingyang-v1-i1-GGUF
Quantization vs wwe180/Llama3-18B-lingyang-v1. mradermacher/Llama3-18B-lingyang-v1-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 157 tensors match exactly and 548 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/157, MLP 0/234, Attention 0/312