The tremendous gain owing to the ubiquitous acceptance of the cloud services across the globe results in more complexity for the cloud providers by way of resource maintenance. This has a direct effect on the cost economy for them if the resources are not efficiently utilized. Most of the allocation strategies follow mechanisms involving direct allotment of VMs onto the servers based on their capabilities. This paper presents a VM allocation strategy that looks at VM placement by allowing server capacity to be partitioned into different classes. The classes are mainly based on the RAM and processing abilities which would be matched with VMs need. When the match is found the servers from this category are provisioned for the task executions. Based on the experimentation for various datacenter scenarios, it has been found that the proposed mechanism results in significant energy savings with reduced response time compared to the traditional VM allocation policies.