Skip to content
HomeSolutionsLenovoLenovo ThinkSystem SR670 V2 — 8x NVIDIA A100 PCIe
Lenovo logo
Lenovo

Lenovo ThinkSystem SR670 V2 — 8x NVIDIA A100 PCIe

Eight proven A100 GPUs for established training and HPC pipelines.

Full manufacturer warrantyAuthorized channel48-hour quote

We help you choose, configure, and deliver the right system — no obligation.

Lenovo ThinkSystem SR670 V2 — 8x NVIDIA A100 PCIe — Lenovo enterprise hardware
Lenovo logo
Lenovo ThinkSystem SR670 V2 — 8x NVIDIA A100 PCIe hardware detail 1
Lenovo ThinkSystem SR670 V2 — 8x NVIDIA A100 PCIe hardware detail 2
Lenovo ThinkSystem SR670 V2 — 8x NVIDIA A100 PCIe hardware detail 3

Configuration at a Glance

GPU / Accelerator8x NVIDIA A100 PCIe (80GB HBM2e each)
GPU InterconnectPCIe Gen4 + optional NVLink bridges
CPU2x Intel Xeon Scalable 3rd Gen (up to 40 cores each)
MemoryUp to 4TB DDR4-3200 (32 DIMM slots)

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.

GPU / Accelerator

8x NVIDIA A100 PCIe (80GB HBM2e each)

Processor

2x Intel Xeon Scalable 3rd Gen (up to 40 cores each)

Memory

Up to 4TB DDR4-3200 (32 DIMM slots)

Storage

Up to 6x EDSFF E1.S NVMe SSD

Overview

This ThinkSystem SR670 V2 is configured with eight NVIDIA A100 PCIe GPUs and dual 3rd Gen Intel Xeon Scalable processors, a proven platform for AI training and accelerated HPC. Nexus Compute specifies, configures, and tests each system through Lenovo-authorized channels with Lenovo warranty and XClarity management.

Who This Solution Is For

Teams expanding established Ampere GPU estates
HPC and research groups on proven platforms
Organizations standardizing on Intel Xeon and A100
Buyers seeking mature, well-supported AI compute

Business Benefits

Proven Ampere platform

The widely-deployed A100 offers mature framework and driver support for predictable results.

Fleet consistency

Matching existing A100 nodes keeps tooling, images, and operations uniform across the estate.

Authorized sourcing

Configured and validated through Lenovo channels with full manufacturer warranty.

Typical Business Use Cases

1

Deep learning model training

2

Accelerated HPC and simulation

3

Multi-GPU data science pipelines

4

Batch inference at scale

Industry Applications

AI & Machine LearningHigher Education & ResearchHealthcare & Life SciencesHPCGovernment & Defense

Technical Overview

The SR670 V2 8-DW GPU model is a 3U platform on 3rd Gen Intel Xeon Scalable 'Ice Lake' processors hosting eight double-wide PCIe Gen4 NVIDIA A100 GPUs with optional NVLink bridges. EDSFF E1.S NVMe storage and redundant Platinum power support sustained accelerated workloads.

GPU / Accelerator8x NVIDIA A100 PCIe (80GB HBM2e each)
GPU InterconnectPCIe Gen4 + optional NVLink bridges
CPU2x Intel Xeon Scalable 3rd Gen (up to 40 cores each)
MemoryUp to 4TB DDR4-3200 (32 DIMM slots)
StorageUp to 6x EDSFF E1.S NVMe SSD
NetworkingOCP 3.0 + PCIe NICs (HDR InfiniBand / 100GbE optional)
Form Factor3U rackmount
PowerUp to 4x 2400W Platinum PSU (redundant)
WarrantyLenovo warranty (configurable terms)

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

Is the A100 still a sensible choice in 2026?

Yes, when matching an existing Ampere fleet or where mature, broadly-validated support matters. We help weigh A100 against newer Hopper options for new build-outs.

Should we add NVLink bridges?

NVLink bridges pair adjacent A100s for higher GPU-to-GPU bandwidth, benefiting multi-GPU training. We configure them based on your parallelism needs.

Can this integrate with our current A100 cluster?

We match GPU, networking, and imaging to your existing nodes for operational consistency and validate before delivery.

Hardware Assistance

Configure the Lenovo ThinkSystem SR670 V2 — 8x NVIDIA A100 PCIe 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.