mradermacher/Qwen2-72B-GGUF
Quantization vs Qwen/Qwen2-72B. mradermacher/Qwen2-72B-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 401 tensors match exactly and 562 within quantization error.
Tensors changed: Embeddings 0/1, MLP 0/240, Attention 0/560, Norms 0/161, lm_head 0/1