mradermacher/Giftige-Blume-31B-v1-StyleSwap-i1-GGUF
Quantization (fewer layers) vs Casual-Autopsy/Giftige-Blume-31B-v1-StyleSwap. mradermacher/Giftige-Blume-31B-v1-StyleSwap-i1-GGUF matches part of Casual-Autopsy/Giftige-Blume-31B-v1-StyleSwap (773 of its 1188 tensors; the rest of Casual-Autopsy/Giftige-Blume-31B-v1-StyleSwap has no counterpart). On the shared part: mradermacher/Giftige-Blume-31B-v1-StyleSwap-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 361 tensors match exactly and 412 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230