mradermacher/Qwen-72B-GGUF
Quantization vs Qwen/Qwen-72B. mradermacher/Qwen-72B-GGUF is a GGUF quantization (Q5_K_S) of the same weights: 241 tensors match exactly and 402 within quantization error.
Tensors changed: Embeddings 0/1, Attention 0/240, Norms 0/161, MLP 0/240, lm_head 0/1