I am not sure how workload specific it is, but in cloud compute in organizations I've worked there's often been a substantial savings outlay from literally just switching from x86 machines for workloads to ARM machines, with no other changes. So it's usually twofold, and a combination of both (lower price for the instance, but also better efficiency as well). In one organization in particular of recent memory we were doing dynamic autoscaling of hundreds of kubernetes nodes simultaneously and were able to project / achieve about 15% conservatively. Just from going x86 -> ARM with no additional changes. Probably some workload that is CPU bound but does not depend on x86 architecturally would benefit from a number significantly higher than that 15%