Dell DGX GB10 128G Large Capacity Running Memory High Speed Solid State Drive AI Deep Learning Computing Workstation

Product Description

Technical Specifications
System Architecture Chipset: GB10 Grace Blackwell Superchip. Combines a 20-core Arm CPU with a Blackwell GPU via NVLink-C2C interconnect. Coherent unified memory architecture.
CPU 20-core Arm v9 processor (10× Cortex-X925 high-performance cores, 10× Cortex-A725 energy-efficient cores)
GPU Blackwell architecture: 6,144 CUDA cores, 5th-generation Tensor Cores (1,000 AI TOPS FP4), 4th-generation RT Cores.
System Memory 28GB LPDDR5X unified memory (256-bit interface, 273GB/s bandwidth). Supports models up to 200B parameters locally.
Networking ConnectX-7 Smart NIC (200Gbps RDMA), 10GbE RJ45 port, Wi-Fi 7 + Bluetooth 5.3.
Interfaces 4× USB4 Type-C (40Gbps), 1× HDMI 2.1a (8K output), Multichannel audio support.
Power & Cooling 170W typical operation (up to 224W peak). Passive airflow design for silent operation.
Physical Specs 150mm x 150mm x 50.5mm. Weight: 1.2kg. Form Factor: FHFL dual-slot.
AI Software Stack DGX OS (Ubuntu 22.04), AI Enterprise software stack, PyTorch, TensorFlow, RAPIDS, cuDNN, TensorRT.
Cyber Resilient Architecture

Security is integrated into every phase of the lifecycle, including protected supply chain and factory-to-site integrity assurance. Silicon-based root of trust anchors end-to-end boot resilience.

Autonomous Collaboration

Increase efficiency and accelerate operations with autonomous collaboration. Simplify, automate and centralize management with advanced enterprise consoles.

Sustainability

Designed with recycled materials and innovative energy efficiency options to reduce carbon footprint and lower operation costs throughout the product lifecycle.

Enterprise-Grade Performance

Designed for 24x7 enterprise data center operations, featuring enterprise-grade components and energy-efficient hardware optimized for deployment at scale.

Supports Secure Boot with Hardware Root of Trust technology, providing an extra layer of security, and meets NEBS Level 3 standards to comply with modern data center requirements.

The passively cooled, energy-efficient design fits a wide range of Tesla-Certified systems and is easy to integrate into existing infrastructure.

Frequently Asked Questions
Q1: What are the primary AI model capabilities of this system?
The system supports local inference for models up to 200B parameters (e.g., LLaMA 2, DeepSeek-R1) and fine-tuning for models up to 70B parameters. It can scale to 405B parameters via dual-node clustering.
Q2: Does the hardware include built-in security features?
Yes, it features a Cyber Resilient Architecture with Secure Boot, Silicon-based root of trust, ECC memory protection, and confidential computing through ARM TrustZone.
Q3: What kind of networking performance can I expect?
The system is equipped with a ConnectX-7 Smart NIC providing 200Gbps RDMA for high-speed clustering, a 10GbE RJ45 port, and the latest Wi-Fi 7 (802.11be) connectivity.
Q4: Is the system suitable for a quiet office or laboratory environment?
Absolutely. It uses a passive airflow design optimized for silent operation, making it ideal for environments where noise reduction is critical.
Q5: What software comes pre-installed for AI development?
The system comes with DGX OS (Ubuntu-based) and a comprehensive AI Enterprise software stack, including PyTorch, TensorFlow, RAPIDS, and NVIDIA NGC container access.
Q6: What are the power requirements for standard operation?
Typical operation consumes approximately 170W, with a peak consumption of up to 224W under heavy computational loads.

Related Products