Solutions built for data-intensive applications,
optimized to leverage NVIDIA GPU co-processing
NVIDIA GPU Co-Processing
Supports two to four Nvidia dual-wide GPUs for co-processing to enable higher bandwidth and improved data-transfer rates, as well as advanced AI / machine learning applications
High-Density, High-Performance
Featuring the latest professional-grade AMD EPYC or Intel Xeon processors and high-speed memory for data-heavy processing
Extensive On-Board Storage
Front-removable SSDs up to 30.72TB each
Nucleus GPU AI Enabled Recorder rack-mount systems are built for data-intensive applications, and available in a variety of configurations and form factors to meet your exact needs. Whether you need powerful NVIDIA GPU AI co-processing, expansive data storage, or a combination of both, Nucleus GPU AI Enabled Recorders are the right tool for high-speed data ingest, processing, and recording as well as AI / Machine Learning analytics and Large Language Models (LLM).
All systems feature:
- Available with AMD EPYC 3rd and 4th generation processor with up to 96 cores / 194 threads or the latest 3rd and 4th generation Intel Xeon Scalable Processors
- Remote Management, IPMI, HTML5 and API based out of band management with MAC addresses identification, one time boot on next reboot option, PXE boot option, Redfish compatible Out of Band (OBB) management connection
- Certified for CentOS, Red Hat Enterprise Linux, VMware vSphere, Windows 2019 server, Windows 10
- Air cooling with heatsink achieves lower power-usage effectiveness (PUE) and optimized TCO for data centers
- Tool-less design for easy serviceability
- Includes service and maintenance documents for easy field access, service, and installation of PCIe cards
- Compliant with the NextComputing Supply Chain Risk Management Process
The Nvidia Advantage
AI and Data Science
Transform any enterprise into an AI organization with NVIDIA AI, the world’s most advanced platform with full stack innovation across accelerated infrastructure, enterprise-grade software, and AI models. By accelerating the entire AI workflow, projects reach production faster, with higher accuracy, efficiency, and infrastructure performance at a lower overall cost.
Machine Learning
Machine learning helps businesses understand their customers, build better products and services, and improve operations. With accelerated data science, businesses can iterate on and productionize solutions faster than ever before all while leveraging massive datasets to refine models to pinpoint accuracy.
1U Form Factor
Storage
Options for up to 10 all-flash NVMe drives on front panel and four drives on middle panel to enable extensive storage and high-throughput performance, -or- up to 4 front-removable NVMe SSDs
NVIDIA GPU Co-Processing
2 to 4 front-accessible Nvidia dual-wide GPUs for co-processing to enable higher bandwidth and improved data-transfer rates as well as advanced AI / machine learning applications
2U Form Factor
Deployable
Operate the system from within the rugged, TSA-compliant travel case for quick setup anywhere.
Storage
Up to 8 NVMe SSDs to 61.44TB each
NVIDIA GPU Co-Processing
Options for NVIDIA RTX A2000 / RTX 4000 SFF ADA and A2 Tensor Core GPU(s) for Artificial Intelligence (AI)/machine learning at the Edge
3U Form Factor
Storage
Up to 8 front-removable NVMe SSDs up to 61.44TB each
NVIDIA GPU Co-Processing
Up to two Nvidia dual-wide GPUs for co-processing to enable higher bandwidth and improved data-transfer rates as well as advanced AI / machine learning applications
Start Building Your Solution
A NextComputing Sales Engineer is available by phone or email to answer any questions and to help you build the perfect solution for your specific requirements.
System Specs
| Processor |
|
|---|---|
| Memory |
3200 MHz RAM to 2TB |
| GPU Expansion |
|
| Storage |
|
| Sustained Read/Write | NVME to 3.5GB/second per drive |
| Network |
|
| AI |
Options for NVIDIA A2 Tensor Core GPU(s) for Artificial Intelligence (AI)/machine learning at the Edge |
| Security | Secure Boot UEFI compliant BIOS, Boot Guard, TPM2.0 |
| Remote Management | IPMI, HTML5 and API based out of band management with MAC addresses identification, one time boot on next reboot option, PXE boot option, Redfish compatible Out of Band (OBB) management connection |
| Available Operating Systems |
|
| Power |
1+1 Redundant 800W 80 PLUS Platinum Power Supply |
| Environmental |
|
| Warranty | 1 year parts and labor. 2nd and 3rd year warranty options |
| Purpose-Built Solutions | Private label branding options. Purpose built application integration and configuration control management services. |
Resources
Nucleus GPU AI Enabled Recorder Datasheet
Speak to a Sales Engineer
Additional Services
