ND911/Flan-t5-xxl-F16_ggufs
Quantization vs google/flan-t5-xxl. ND911/Flan-t5-xxl-F16_ggufs is a GGUF quantization (Q2_K) of the same weights: 124 tensors match exactly and 434 within quantization error.
Tensors changed: Attention 0/290, Norms 0/122, other 0/145, lm_head 0/1