The emergence of Cloud Computing (CC) has rapidly changing the thinking of IT service providers, which propose actually a proliferation of services based on virtualization technology. This paradigm contributes to the built of multiple data centers across the world housing millions of Virtual Machines (VMs). In this context, Virtual Machine Placement (VMP) is considered as one of the greatest challenges to overcome by cloud providers in order to optimize their platforms by improving power efficiency, resource utilization, and Quality of Services (QoS). In this paper, we propose a multi-objective framework based on hybrid Tabu Search (TS) and Genetic Algorithm (GA) for the VMP problem. The proposed approach is tested on real cloud platforms and compared with some existing methods from the literature. Evaluation results show that the proposed technique is more efficient and fully competitive than other methods in the literature.