mradermacher/MS3.2-PaintedFantasy-Visage-v4-34B-i1-GGUF
Quantization vs zerofata/MS3.2-PaintedFantasy-Visage-v4-34B. mradermacher/MS3.2-PaintedFantasy-Visage-v4-34B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 119 tensors match exactly and 415 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/119, MLP 0/177, Attention 0/236