Chapter 1. About Red Hat AI validated models
Red Hat AI validated models have been tested and verified to work correctly across supported hardware and product configurations. These models are available as Hugging Face downloads, as OCI artifact images, and as modelcar container images. Platform-specific validated models are also available for IBM Spyre on IBM Power and IBM Z systems.
If you are using AI Inference Server as part of a RHEL AI deployment, use OCI artifact images.
If you are using AI Inference Server as part of a OpenShift AI deployment, use ModelCar images.
Red Hat uses GuideLLM for performance benchmarking and Language Model Evaluation Harness for accuracy evaluations.
Explore the Red Hat AI validated models collections on Hugging Face.
AMD GPUs support FP8 (W8A8) and GGUF quantization variant models only. For more information, see Supported hardware.