Build. Run. Scale.

Everything you need to build, run, and deploy Agentic AI, RAG, and Sovereign AI solutions.

Type at least 3 characters to search

Open & interoperableBuilt on open standards and best-in-class tools.
Enterprise readySecure, scalable, and optimized for your production needs.
Optimized performanceIndustry-leading performance across edge, cloud, and on-prem.

Docker - Intel® Inference Microservices

Serve an optimized LLM in one command.

bash

docker run --rm -p 8000:8000 \
  --cap-add SYS_NICE \
  --shm-size=2g \
  intel/inference-xeon-qwen-qwen3-4b:0.1.0

Send a simple request.

bash

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-4B",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Review the prerequisites before running the commands.

View full quickstart guide

Start building

Models ready to serve with Intel Inference Microservices. Copy a ready-to-run Docker command from any card.

Developer docs

Intel® Inference MicroservicesDeploy and serve models with high performance.
Intel® AI for Enterprise SolutionsDeploy production-ready enterprise AI in minutes.
Intel® AI for Enterprise InferenceDeploy and scale inference at enterprise grade.
Intel® AI for Enterprise RAGDocumentation coming soon - in the meantime, explore the project repository.
Intel® AI for Enterprise Agent ToolkitDocumentation coming soon - in the meantime, explore the project repository.