VMware Cloud Foundation: AI Models Now On-Premises

Leading AI models, including Nemotron 3, Gemma 4, cotomi, Qwen3.7-Max, and GLM-5.2, are now validated to run on VMware Cloud Foundation. This means organizations can bring these AI models on-premises and offer them as a service. Broadcom announced this development, highlighting that these models come from providers like Google, NVIDIA, NEC, Alibaba Cloud, and Z.ai. Many enterprises are moving inference workloads to private clouds due to privacy and security concerns. VMware Cloud Foundation offers an AI- and Kubernetes-native platform for deploying a wide variety of AI models. Broadcom's Private Cloud Outlook 2026 indicates that 56% of enterprises are already running or planning to run production AI inferencing on private cloud. VCF provides a unified private cloud platform that can handle inference workloads, agentic applications, containerized services, and traditional virtual machines. Independent benchmark testing confirms VCF delivers performance on par with bare metal. This offers organizations a production-ready path to deploying diverse AI models securely and cost-effectively.