Lenovo ThinkSystem SR860 V3 — 4-Socket with 4x NVIDIA L40S
Four L40S GPUs for cost-efficient inference, generative AI serving, and VDI.
We help you choose, configure, and deliver the right system — no obligation.
Configuration at a Glance
Tailored per engagement. Full technical overview below.
Configuration Options
Core specifications for this system. Every component is configurable to your workload — request a quote for a tailored build.
4x NVIDIA L40S (48GB GDDR6 each)
4x Intel Xeon Scalable (4th/5th Gen)
Up to 4TB DDR5 (configurable)
NVMe / SAS hot-swap (configurable); M.2 boot
Overview
This ThinkSystem SR860 V3 is configured with four NVIDIA L40S accelerators to balance inference throughput, generative AI serving, and graphics-rich VDI on a single four-socket node. It is integrated, validated under mixed GPU load, and delivered warranty-backed through Lenovo-authorized distribution.
Who This Solution Is For
Business Benefits
Versatile acceleration
The L40S handles inference, fine-tuning, and graphics workloads, maximizing utilization of a single shared platform.
Efficient cost-per-stream
Four L40S GPUs deliver strong throughput per watt for serving and VDI without top-tier training-GPU cost.
Headroom to grow
The 4U four-socket chassis leaves room to add GPUs, memory, and storage as demand rises.
Typical Business Use Cases
LLM and generative AI inference serving
Virtual desktop and virtual workstation hosting
Real-time video and rendering pipelines
Mixed AI and visualization workloads
Industry Applications
Technical Overview
The SR860 V3 four-socket platform supports multiple double-wide GPUs over PCIe Gen5; this build pairs four NVIDIA L40S accelerators with 4th/5th Gen Intel Xeon Scalable CPUs and DDR5 memory. The XClarity Controller, redundant power, and flexible NVMe storage make it a dependable shared inference and VDI host.
| GPU / Accelerator | 4x NVIDIA L40S (48GB GDDR6 each) |
| CPU | 4x Intel Xeon Scalable (4th/5th Gen) |
| Memory | Up to 4TB DDR5 (configurable) |
| Storage | NVMe / SAS hot-swap (configurable); M.2 boot |
| Networking | OCP 3.0 + PCIe Gen5; 25/100GbE |
| Form Factor | 4U four-socket rackmount |
| Management | Lenovo XClarity Controller |
| Power | Redundant hot-swap PSUs (N+1) |
| Warranty | Lenovo 3-year (upgradeable to 5-year, on-site) |
Specifications are indicative and configured to each engagement. Request a quote for a configuration tailored to your requirements.
Warranty, Support & Fulfillment
Every system ships from an authorized channel, configured and tested, with the documentation enterprise buyers need — backed by warranty and a dedicated account team.
Enterprise Warranty
Full manufacturer warranty with optional on-site, next-business-day support and extended coverage.
Authorized Channel
Sourced through Tier-1 distribution and OEM partners — never grey market. Asset & warranty records included.
Lead Time & Deployment
48-hour quotes, then configured, burn-in tested, and delivered on a committed schedule.
Nationwide Fulfillment
Coordinated logistics, rack-and-stack, and delivery wherever your infrastructure lives.
Frequently Asked Questions
L40S or H100 for our workload?
For inference, generative AI serving, fine-tuning, and VDI, the L40S offers excellent value and versatility; the H100 is better for large-scale training. We match the GPU to your dominant workload.
How many VDI users can this support?
User density depends on profile (knowledge worker versus 3D designer) and vGPU sizing. Four L40S GPUs support substantial mixed VDI; we size vGPU profiles to your user mix.
Can we expand the GPU count later?
Yes — the SR860 V3 supports additional double-wide GPUs within the chassis, so capacity can grow with demand under power and cooling constraints.
Hardware Assistance
Configure the Lenovo ThinkSystem SR860 V3 — 4-Socket with 4x NVIDIA L40S with Nexus Compute
Tell us your requirements and a hardware specialist will help you specify, configure, and quote the right system — typically within two business days. No obligation.