-
Products & documentation Red Hat AI
A platform of products and services for the development and deployment of AI across the hybrid cloud.
Red Hat AI Enterprise
Build, develop, and deploy AI-powered applications across the hybrid cloud.
Red Hat AI Inference
Optimize model performance with an integrated stack for fast, consistent, and cost-effective inference at scale.
Red Hat OpenShift AI
Build and deploy AI-enabled applications and models at scale across hybrid environments.
-
Learn Basics
-
AI partners
Red Hat Enterprise Linux AI
Red Hat® Enterprise Linux® AI is a platform for running large language models (LLMs) in individual server environments. It includes Red Hat AI Inference for fast, consistent, and cost-effective inference across the hybrid cloud.
Please note: Red Hat Enterprise Linux AI is no longer available for new customers. Its capabilities—including vLLM and image mode for Red Hat Enterprise Linux—continue in Red Hat's consolidated inference offering, Red Hat AI Inference. Existing customers remain fully supported.
What is Red Hat Enterprise Linux AI?
Red Hat Enterprise Linux AI brings together 2 moving parts:
- Red Hat AI Inference, which provides the operational control to run any model on any accelerator in any environment.
- A bootable image of Red Hat Enterprise Linux, including hardware-optimized inference and popular AI libraries like PyTorch.
Fast, flexible inference
Red Hat AI Inference is powered by vLLM and llm-d. This allows the end-to-end inference stack to optimize cost-per-token and hardware capacity for faster response times.
Packaging the operating system and the inference server together provides Day 1 operations, so you can begin serving and scaling models of your choice in the environment that’s best for you.
Benefits
Open source gen AI models
Access enterprise-grade, open source Granite family models.
Cost-effective inference
Optimize GPU usage with vLLM to increase efficiency without sacrificing performance.
Flexible, consistent deployment
Run models where you need them—datacenters, clouds, or at the edge—on diverse hardware and operating systems.
233% ROI with Red Hat AI
Red Hat commissioned Forrester Consulting to conduct a Total Economic Impact™ (TEI) study and examine the potential return on investment (ROI) enterprises may realize by deploying Red Hat AI.
After interviewing Red Hat AI customers, the analysis found that a composite organization realized an ROI of 233% over 3 years, representing a total value of more than triple their initial investment.1
Product highlights
| Feature | Details | Benefit |
|---|---|---|
LLMs for the enterprise | Tune smaller, purpose-built models with your own data. | Flexible model tuning and deployment options allow your teams to move faster on your own terms. |
Optimized bootable model runtime instances | Manage your AI platform as a container image. Granite models are packaged as bootable Red Hat Enterprise Linux images via image mode. This includes PyTorch, required runtime libraries, and hardware accelerators for NVIDIA. | Simple, consistent approach to building, deploying, and managing the operating system using container technologies. |
vLLM | Maximize throughput and minimize latency by optimizing GPU usage. | Efficient inference with lower cost-per-token. |
LLM Compressor | Compress foundational and trained models of any size to reduce compute use and its related costs. | Faster model inference, without altering data quality or response accuracy. |
Hybrid cloud portability | Use a unified, high-performance platform that supports your business needs—wherever your data resides. | Run your choice of models across various accelerators, Kubernetes, and Linux environments. Integrate with observability tools for enhanced monitoring that also support LLM APIs, such as OpenAI’s, for flexible deployment. |
Optimized model repository | Access a collection of pre-optimized models that includes support for both vLLM and NVIDIA NIMs. | Ready-to-go model deployments for faster inference for the enterprise. |
Enterprise-grade technical support | Get hands-on support as well as Open Source Assurance legal protections. | Ask Red Hat AI experts and consultants so you don’t have to guess or slow down. |
Why choose Red Hat AI?
Build on a trusted foundation that supports any model and any agent on any hardware accelerator—across the hybrid cloud. Red Hat AI gives organizations the freedom to deploy where their data, compliance, and cost requirements demand.
Inference
Manage model complexity with fast, efficient inference powered by vLLM and the control to run any model on any accelerator across the hybrid cloud.
Data
Customize domain-specific agentic AI use cases with models connected to your organization’s own private data.
Agents
Simplify and accelerate your journey to successful agentic AI adoption with governance and control.
Platform
Deploy resilient, trustworthy AI solutions on a foundation of open source transparency and hybrid cloud scalability.
Deploy with partners
Experts and technologies are coming together so our customers can do more with AI. Explore all of the partners working with Red Hat to certify their operability with our solutions.
Explore more AI resources
Use cases for fast, efficient inference
Why you should care about inference
Talk to a Red Hatter about Red Hat AI
1Forrester Consulting study, commissioned by Red Hat. “Forrester Total Economic Impact™ Of Red Hat AI." February 2026.
