mradermacher/GUI-Owl-1.5-8B-Think-i1-GGUF
Quantization (fewer layers) vs mPLUG/GUI-Owl-1.5-8B-Think. mradermacher/GUI-Owl-1.5-8B-Think-i1-GGUF matches part of mPLUG/GUI-Owl-1.5-8B-Think (399 of its 750 tensors; the rest of mPLUG/GUI-Owl-1.5-8B-Think has no counterpart). On the shared part: mradermacher/GUI-Owl-1.5-8B-Think-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1