Sold by: Red Hat Limited
Deployed on AWS
Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models (LLMs) for enterprise applications.
4.5
Overview
Red Hat Enterprise Linux AI is a foundation model platform for running LLMs in individual server environments. The solution includes the Red Hat AI Inference Server, which provides an immutable, purpose-built appliance optimized for inference. Packaging the OS and application together, Red Hat Enterprise Linux AI facilitates Day 1 operations to optimize model inference across the hybrid cloud. Its vLLM runtime maximizes throughput and minimizes latency. This is complemented by LLM compressor and Speculators for further model optimization and a pre-optimized model repository, ensuring fast and cost-effective deployments.
Highlights
- The Granite family of LLMs.
- A bootable image, including AI libraries such as PyTorch, and optimized inference for NVIDIA and enterprise-grade technical support.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Rhel 9.6
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
p5.48xlarge Recommended | $0.40 |
p4d.24xlarge | $0.40 |
g6e.48xlarge | $0.40 |
Dimensions summary
You pay by the hour based on the GPU-accelerated compute instance you run. The three dimensions map to specific instance types: p5.48xlarge, p4d.24xlarge, and g6e.48xlarge. Each represents a different accelerator configuration, so your rate changes with the instance you select. Pricing scales with usage — you are billed for the hours each instance runs, with no upfront commitment. The license is priced per accelerator and includes all components needed to run large language models in a single server environment.
Top-of-mind questions for buyers
Each dimension maps to a specific GPU-accelerated instance type: p5.48xlarge, p4d.24xlarge, or g6e.48xlarge. You are billed per hour that instance runs. The license is priced per accelerator, so the number of accelerators in your chosen instance shapes your rate.
Hourly charges apply while an instance runs. When you stop or terminate the instance, the hourly software charge stops accruing. Underlying AWS storage or reserved resources may still bill separately, but the software license meters running hours only.
The instance type you select drives your rate. Each of the three dimensions carries a different accelerator configuration, so the p5.48xlarge, p4d.24xlarge, and g6e.48xlarge rates differ. You do not combine dimensions; you pick one instance and pay its hourly rate for the hours it runs.
www.redhat.com
Helpful?
Vendor refund policy
All fees are non-refundable.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
- Launch the product via 1-Click or the marketplace listing.
- Access your instance using ssh
- Open an SSH client
- Locate your private key file that was used to launch this instance. This file was downloaded when you created the key pair in AWS.
- Navigate to the directory where your .pem key file is located by using the command: cd path/to/your-key-file-directory.
- Set the permissions of your .pem file to ensure it is not publicly viewable by using the command: chmod 400 your-key-file.pem.
- Use the default username 'cloud-user' and the ssh key registered with AWS. Note that 'root' is disabled by default. Replace your-key-file.pem with your key file name and your-instance-public-dns with the public DNS or IP address of your instance.
Additional details
Usage instructions
Support
Vendor support
Get answers quickly by opening a support case with us at
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models (LLMs) for enterprise applications.
Red Hat AI Enterprise is an integrated AI platform for deploying and managing efficient and cost-effective AI models, agents and AI-powered applications across hybrid cloud environments. It unifies AI model and application lifecycles to increase efficiency, accelerate delivery, and mitigate risk by providing a ready-to-use development environment with enterprise-grade capabilities. This platform is a tested, supported AI stack, powered by Red Hat OpenShift, that enhances interoperability and ensures business continuity. It includes core capabilities like model tuning, high-performance inference, agentic AI workflow management - with the flexibility to support any model, use any hardware, and deploy anywhere while meeting data location requirements.
Red Hat Enterprise Linux is the consistent foundation for the enterprise hybrid cloud - providing the tools needed to deliver services and workloads faster with less effort.
Red Hat AI Enterprise is an integrated AI platform for deploying and managing efficient and cost-effective AI models, agents and AI-powered applications across hybrid cloud environments. It unifies AI model and application lifecycles to increase efficiency, accelerate delivery, and mitigate risk by providing a ready-to-use development environment with enterprise-grade capabilities. This platform is a tested, supported AI stack, powered by Red Hat OpenShift, that enhances interoperability and ensures business continuity. It includes core capabilities like model tuning, high-performance inference, agentic AI workflow management - with the flexibility to support any model, use any hardware, and deploy anywhere while meeting data location requirements.
Customer reviews
Deependra S.
Model workloads now feel like regular infrastructure
Reviewed on Sep 19, 2026
Review provided by G2
What do you like best about the product?
Using RHEL AI does not feel like starting with a completely new/different platform just because the use cases are AI, the Red Hat's familiarity is still there and this makes it very much easier to use and the capabilities of Red Hat are known to everyone who has used Linux.
What do you dislike about the product?
Red Hat's documentation is very confusing for Linux AI. It always confuses me whether the issue that is being populated is caused by a model or if the images have any problems. I would really like to see this fixed soon.
What problems is the product solving and how is that benefiting you?
My organization's infrastructure was introduced very smoothly with RHEL AI along with the projects, which was a hasty experience earlier and it used to be very dev-centric. With RHEL AI, the path is familiar and model experimenting has become less hasty as the platform team can manage it with more ease.
Pro H.
Reliable AI Platform, But Setup Could Be Simpler
Reviewed on Sep 15, 2026
Review provided by G2
What do you like best about the product?
What I like most is the stability and security when running AI workloads. The integration with the Red Hat ecosystem is also useful, as it makes managing the environment easier. I especially appreciate the consistent performance and the ability to work with AI tools without having to manage every part of the infrastructure manually.
What do you dislike about the product?
The main thing I dislike is that setting up AI workloads can be a little complicated. Getting the right dependencies, configurations, and hardware support working together may take some trial and error. For someone who is new to Red Hat or enterprise AI, the initial setup and troubleshooting could be more straightforward.
What problems is the product solving and how is that benefiting you?
It helps solve the problem of setting up and managing AI workloads in a stable enterprise environment. I find it useful because it brings the AI tools and infrastructure together with the existing Red Hat ecosystem, so there is less manual configuration and troubleshooting. The performance has also been consistent, and the security and reliability are helpful when working with enterprise applications. Overall, it saves some setup time and makes it easier to focus on the actual AI work.
Leo G.
Deploy and Manage Multiple Models Seamlessly in One Console
Reviewed on Sep 11, 2026
Review provided by G2
What do you like best about the product?
With this one I am able to deploy several models and control their behaviour within one console.
What do you dislike about the product?
Sometimes it might not be too user friendly.
What problems is the product solving and how is that benefiting you?
It helps us by giving us better visibility into what’s deployed, where and when it was deployed, and how it’s performing.
Computer Software
Simple, Reliable Way to Use AI Tools Securely
Reviewed on Aug 28, 2026
Review provided by G2
What do you like best about the product?
It is very simple to manage and is reliable. It makes it easier to use AI tools in a secure manner.
What do you dislike about the product?
Troubleshooting issues can be difficult because there are many components involved, such as the model server, containers, and system resources.
What problems is the product solving and how is that benefiting you?
RHEL AI helps solve the problem of deploying and managing AI models in a secured and controlled environment. It helps me by providing a more consistent environment for testing, deploying and managing AI models, while giving better control over security and overall infrastructure.
Shashank s.
Enterprise-Ready Granite LLMs with Full Support and Legal Indemnification
Reviewed on Aug 25, 2026
Review provided by G2
What do you like best about the product?
One of the best parts I like about Red Hat is the Enterprise Granite models. RHEL AI includes access to the open source Granite family of LLMs developed by IBM Research. A major enterprise benefit is that these models are fully supported and legally indemnified by Red Hat.
What do you dislike about the product?
From what I’ve observed, one of the biggest selling points of RHELAI is the legal indemnification it offers. However, this protection only applies to the IBM Granite models. If I choose to run other open-source models, like Llama 3 or Mistral, on the platform, I lose that legal safety net, along with the specific enterprise support tied to the model itself. Even though it has a built in LLM compressor but running the Enterprise create generative AI requires serious hardware.
What problems is the product solving and how is that benefiting you?
For me, it’s an optimized, ready-to-use application that lowers the barrier to entry for Enterprise AI. It packages the operating system, AI models, and inference software together, so businesses can deploy AI without needing extensive data science expertise or having to deal with complex integration barriers. A few of the components and tools it provides are genuinely beneficial—for example, Red Hat AI inference, Enterprise granite models, bootable AI appliances, and the LLM compressor. When it comes to cost-effectiveness and efficiency, it generally improves GPU utilization and helps compress models. As a result, RHEL AI can significantly lower the compute cost and the cost per token associated with running generative AI.