torchsnow/Ministral-3-8B-Uncensored-Q5_K_S-GGUF
Quantization (fewer layers) vs Felldude/Ministral-3-8B-Uncensored. torchsnow/Ministral-3-8B-Uncensored-Q5_K_S-GGUF matches part of Felldude/Ministral-3-8B-Uncensored (309 of its 531 tensors; the rest of Felldude/Ministral-3-8B-Uncensored has no counterpart). On the shared part: torchsnow/Ministral-3-8B-Uncensored-Q5_K_S-GGUF is a GGUF quantization (Q5_K_S) of the same weights: 69 tensors match exactly and 240 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/136