IBM Launches Red Hat AI Inference for 70B Models and OpenShift Virtualization Service
IBM rolled out Red Hat AI Inference on IBM Cloud with built-in governance and support for models like Llama 3.3 70B and GPT-OSS-120B, offering high-throughput, low-latency production-grade performance. It also introduced Red Hat OpenShift Virtualization Service on IBM Cloud to migrate and manage VM workloads securely at scale.
1. New Managed AI Inference Service
IBM Cloud now offers Red Hat AI Inference as a fully managed service featuring built-in governance controls, audit logging, and privacy safeguards. The service supports high-throughput, low-latency production workloads and a model catalog including Granite 4.0 H Small, Mistral-Small-3.2-24B-Instruct, Llama 3.3 70B, GPT-OSS-120B and Nemotron-3-Nano-30B-FP8, with additional models planned from May 2026.
2. OpenShift Virtualization Service Launch
Red Hat OpenShift Virtualization Service on IBM Cloud provides enterprises a managed path to migrate and operate virtual machines on Kubernetes-based infrastructure. The service offers automated lifecycle management, predictable cost structures and enterprise-grade security to support workloads at scale while easing the transition toward containerization.
3. Strategic Hybrid Cloud Expansion
These two offerings extend IBM’s full spectrum of Red Hat managed platforms—Red Hat Enterprise Linux, OpenShift, Ansible Automation and AI—positioning IBM Cloud as a one-stop hybrid cloud foundation. By enabling production-grade AI inference and secure virtualization, IBM targets accelerated enterprise adoption of hybrid cloud and AI, potentially driving service revenue growth.