skip to main content

Scaling Enterprise AI: High-Density CPU Inferencing with Lenovo ThinkSystem SR650 V4 and Intel Xeon 6

Solution Brief

Home
Top
Published
14 Jan 2026
Form Number
LP2363
PDF size
4 pages, 136 KB

Abstract

The Lenovo ThinkSystem SR650 V4, powered by Intel® Xeon® 6 processors, provides a scalable and cost-effective foundation for enterprise generative AI. Engineered to meet the performance demands of real-time AI workloads, the platform supports approximately 96 to 110 concurrent users per server while maintaining response times below 100 milliseconds. With sustained throughput exceeding 1,000 tokens per second and consistent performance across both bare-metal and containerized environments, the SR650 V4 enables enterprises to deploy high-density, CPU-only AI inferencing solutions that deliver fast, reliable, and responsive user experiences for business-critical applications.

Related product families

Product families related to this document are the following: