mmnga/karakuri-vl-32b-thinking-2507-exp-gguf
Quantization (fewer layers) vs karakuri-ai/karakuri-vl-32b-thinking-2507-exp. mmnga/karakuri-vl-32b-thinking-2507-exp-gguf matches part of karakuri-ai/karakuri-vl-32b-thinking-2507-exp (771 of its 1161 tensors; the rest of karakuri-ai/karakuri-vl-32b-thinking-2507-exp has no counterpart). On the shared part: mmnga/karakuri-vl-32b-thinking-2507-exp-gguf is a GGUF quantization (Q8_0) of the same weights: 321 tensors match exactly and 450 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1