Red Hat Enterprise Linux AI
A bootable Red Hat Enterprise Linux image that arrives with IBM Granite models and the InstructLab tuning tools already fitted together.
RHEL AI packages a bootable Red Hat Enterprise Linux image, IBM Granite models, and InstructLab into one foundation model platform, built around the LAB method from IBM Research. Version 1.4, released in February 2025, added Granite 3.1 8B support and a 128k context window. It is aimed at getting a first working model running without assembling the stack by hand. It is not the product IBM names as a Spyre Accelerator requirement: that remains Red Hat AI Inference Server or Red Hat OpenShift AI.
Related Terms
InstructLab
An open source project from IBM Research and Red Hat that lets a subject matter expert add knowledge to a model without being a data scientist.
IBM Granite
IBM's own family of open language models, published under the Apache 2.0 licence so they can be downloaded, tuned, and run on hardware you own.
Red Hat AI Inference Server
Red Hat's model serving product, built on the open source vLLM engine. IBM lists it as one of two supported ways to drive a Spyre Accelerator on IBM Power.