ThinkSystem SR630 V3 with 3x NVIDIA L4 1U Edge Inference Server
Compact 1U AI inference at the edge with three low-power GPUs
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.
3x NVIDIA L4 24GB (Ada Lovelace, single-width, ~72W)
2x Intel Xeon Gold 6542Y (5th Gen, 24 cores each)
512GB DDR5 (16x 32GB RDIMM, 5600 MHz)
6x 2.5-inch NVMe Gen5 hot-swap SSDs
Overview
This SR630 V3 pairs dual Xeon processors with three single-width NVIDIA L4 GPUs for power-efficient inference in space-constrained edge and telco sites. Nexus Compute specifies, configures, and tests each unit, delivering it warranty-backed through authorized Lenovo channels.
Who This Solution Is For
Business Benefits
Edge-ready footprint
Three GPUs in a single rack unit bring inference to sites where space and power are tight.
Energy-efficient acceleration
NVIDIA L4 GPUs deliver strong inference-per-watt at just 72W each within the 1U thermal envelope.
Configured and tested
Each node ships pre-validated with drivers and firmware set, backed by Lenovo onsite warranty.
Typical Business Use Cases
Real-time video analytics
Generative AI inference at the edge
Recommendation and ranking serving
Speech and language inference
Industry Applications
Technical Overview
The Lenovo ThinkSystem SR630 V3 supports up to three single-width 75W-class GPUs in its 1U chassis, here populated with NVIDIA L4 Ada-architecture accelerators. Dual 5th Gen Intel Xeon Scalable processors and PCIe Gen5 lanes feed the GPUs and NVMe storage for compact, distributed inference nodes.
| GPU | 3x NVIDIA L4 24GB (Ada Lovelace, single-width, ~72W) |
| CPU | 2x Intel Xeon Gold 6542Y (5th Gen, 24 cores each) |
| Memory | 512GB DDR5 (16x 32GB RDIMM, 5600 MHz) |
| Storage | 6x 2.5-inch NVMe Gen5 hot-swap SSDs |
| Networking | OCP 3.0 dual-port 25GbE |
| Form Factor | 1U rack |
| Management | Lenovo XClarity Controller (XCC) |
| Power | Dual redundant 1100W 80 PLUS Titanium PSUs |
| Warranty | 3-year Lenovo onsite limited warranty, 9x5 NBD |
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
Why choose L4 GPUs over larger accelerators for the edge?
The NVIDIA L4 runs at roughly 72W with passive single-width cooling, so three fit a 1U chassis without the power and thermal demands of double-wide GPUs, ideal for edge and telco sites.
What inference workloads suit this configuration?
It targets video analytics, small-to-mid LLM serving, recommendation, and speech inference where throughput-per-watt and a compact footprint matter more than peak training performance.
Can these nodes scale horizontally?
Yes. The 1U form factor is designed for distributed deployment; we help size cluster counts and networking to your aggregate inference throughput.
Hardware Assistance
Configure the ThinkSystem SR630 V3 with 3x NVIDIA L4 1U Edge Inference Server 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.