mradermacher/Qwen2.5-72B-2x-Instruct-TIES-v1.0-i1-GGUF
Quantization vs BenevolenceMessiah/Qwen2.5-72B-2x-Instruct-TIES-v1.0. mradermacher/Qwen2.5-72B-2x-Instruct-TIES-v1.0-i1-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 401 tensors match exactly and 562 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/560