mradermacher/MIST-1-140B-GGUF
Quantization vs olaverse/MIST-1-140B. mradermacher/MIST-1-140B-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 317 tensors match exactly and 1108 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/317, MLP 0/474, Attention 0/632