Hardware Datasheet · GPU Server
Nexus Compute
Nexus Compute L4 24-GPU Scale-Out Inference & Video Server
Twenty-four 72W L4 GPUs for power-efficient inference at scale.
Overview
This 2U platform packs up to 24 single-slot NVIDIA L4 24GB GPUs to maximize parallel inference and video throughput per rack-unit at low power. Nexus Compute specifies, assembles, and tests the system around the target serving stack and delivers it warranty-backed through authorized channels.
Specifications
| GPU | Up to 24x NVIDIA L4 24GB GDDR6 (72W, single-slot) |
| GPU Interconnect | PCIe Gen4 x16 across multiple root complexes |
| CPU | Dual AMD EPYC or Intel Xeon |
| Memory | Up to 3TB DDR5 ECC |
| Storage | Hot-swap NVMe (configurable capacity) |
| Networking | Dual 25/100GbE; OCP 3.0 |
| Form Factor | 2U rackmount |
| Power | Redundant N+1 PSUs |
Typical Use Cases
- ·High-concurrency small-model inference
- ·AI video encode, decode, and analytics
- ·Speech, vision, and embedding microservices
- ·Power-constrained edge inference nodes
Industries
Warranty & Support
Supplied through authorized channels with full manufacturer warranty. On-site, next-business-day support options available. Every system is configured, tested, and documented before delivery, with asset and warranty records provided for enterprise audit requirements.
Request a tailored quote
Configurations are tailored per engagement — contact us for pricing and lead times.
sales@nexus-compute.com
+1 737 276 1016
nexus-compute.com
Specifications are indicative and configured to each engagement. All product names, logos, and trademarks are the property of their respective owners. Nexus Compute is an independent enterprise hardware supplier.