DevQuasar/Tongyi-MAI.MAI-UI-8B-GGUF
Quantization (fewer layers) vs Tongyi-MAI/MAI-UI-8B. DevQuasar/Tongyi-MAI.MAI-UI-8B-GGUF matches part of Tongyi-MAI/MAI-UI-8B (399 of its 750 tensors; the rest of Tongyi-MAI/MAI-UI-8B has no counterpart). On the shared part: DevQuasar/Tongyi-MAI.MAI-UI-8B-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: Embeddings 0/1, MLP 0/108, Norms 0/145, Attention 0/144, lm_head 0/1