featherless-ai-quants/Undi95-MG-FinalMix-72B-GGUF
Quantization vs Undi95/MG-FinalMix-72B. featherless-ai-quants/Undi95-MG-FinalMix-72B-GGUF is a GGUF quantization (Q8_0) 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