is it possiable to shared cached models between two or more comfyui instances

i have two gpus, i excute two comfyui instances ,on different ports and different gpu, these two instances may run the same workflow , and most of the used models was same, but it takes twice ram space , it's two large ram cost, i want to shared these same models among the running instances, it may take less ram space ,is it possiable? thank your for your reply!