Is it possible to use Falcon3 or LLaMA,which are already supported by the CPU,in GPU mode?

[GoNow1231]

[maksi65432]

you can at least try but the standart llama.cpp build is not building it in gpu compability because you need to first read build docs https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md