Calculate --override-tensor for llama.cpp using QWEN models and Pi for 2 GPU

When using two GPU with llama.cpp with --split-mode layer you usually provide a --tensor-split value to fit the proportion of the allocation on each GPU, say you have 16GB + 12GB something like --tensor-split 0.6,0.4 may do. That is a rough division of the models, as vRAM counts and hundreds of MB t