mradermacher/Mistral-Medium-3.5-128B-Eschaton-Uncensored-GGUF
Quantization (fewer layers) vs cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored. mradermacher/Mistral-Medium-3.5-128B-Eschaton-Uncensored-GGUF matches part of cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored (795 of its 1233 tensors; the rest of cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored has no counterpart). On the shared part: mradermacher/Mistral-Medium-3.5-128B-Eschaton-Uncensored-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 177 tensors match exactly and 618 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/177, MLP 0/264, Attention 0/352