MSI EdgeXpert - 13SUS AI Supercomputer 128 GB unified Memory, 4 TB(Based on Nvidia DGX Spark GB10 Blackwell 3Year Warranty
MSI EdgeXpert - 13SUS AI Supercomputer 128 GB unified Memory, 4 TB(Based on Nvidia DGX Spark GB10 Blackwell 3Year Warranty
If you have any questions, you are always welcome to contact us. We'll get back to you as soon as possible, within 24 hours on weekdays.
-
Shipping Information
Use this text to answer questions in as much detail as possible for your customers.
-
Customer Support
Use this text to answer questions in as much detail as possible for your customers.
-
FAQ’s
Use this text to answer questions in as much detail as possible for your customers.
-
Contact Us
Use this text to answer questions in as much detail as possible for your customers.
The MSI EdgeXpert - 13SUS AI Supercomputer redefines desktop AI computing, delivering petaflop-scale performance through the cutting-edge NVIDIA® GB10 Grace Blackwell Superchip. Built for developers, AI researchers, and data scientists, this supercomputer empowers local AI development with advanced features in a compact, desktop-ready form.
Key Features at a Glance
- NVIDIA® Grace Blackwell Architecture
- NVIDIA Blackwell GPU & Arm 20-core CPU
- 128 GB LPDDR5x coherent, unified system memory
- 1000 AI FLOPS (FP4) AI performance
- NVIDIA® NVLink®-C2C CPU-GPU memory interconnect
- 4TB Gen5 NVME.M2 with self-encryption
Advanced NVIDIA Grace Blackwell Architecture
Equipped with the NVIDIA Blackwell GPU and Arm 20-core CPU, the EdgeXpert optimizes data preprocessing and orchestration. This accelerates model tuning and enables real-time inference with greater efficiency for demanding AI tasks.
Revolutionary NVLink®-C2C Technology
Experience ultra-fast data access and transfer with NVLink®-C2C Technology. This provides a seamless CPU+GPU memory model boasting up to five times the bandwidth of PCIe 5.0, crucial for high-speed data flow.
Unmatched AI Computing Power
Leverage 1000 AI TOPS (FP4) Tensor Performance for blazing-fast execution of complex AI workloads at scale. The 128 GB LPDDR5x unified system memory provides the extensive capacity needed for smooth model development, rapid experimentation, and highly efficient inference.
Local LLM Development and Scaling
Run large language models (LLMs) locally with support for up to 200 billion parameters, ensuring data security, low latency, and cost control for your full AI workflow, from prototyping to fine-tuning and inference. Utilize high-performance NVIDIA ConnectX networking to stack two MSI systems, allowing work with AI models up to 405 billion parameters.
Seamless Scaling from Desktop to Cloud
Benefit from NVIDIA’s AI software architecture, allowing you to seamlessly scale your projects from the MSI EdgeXpert desktop to NVIDIA DGX™ cloud or other NVIDIA® accelerated data centers and cloud infrastructures, often with minimal code changes.
Technical Specifications
| Architecture | NVIDIA Grace Blackwell GB10 |
| GPU | NVIDIA Blackwell Architecture |
| CPU | 20 core Arm, 10 Cortex-X925 + 10 Cortex-A725 Arm |
| Tensor Performance | 1000 AI TOPS (FP4, Sparse) |
| System Memory | 128 GB LPDDR5x, unified system memory |
| Memory Interface | 256-bit |
| Memory Bandwidth | 273 GB/s |
| Storage | 1 or 4 TB NVME.M2 with self-encryption |
| USB | 4x USB 3.2 Type C |
| Ethernet | 1x RJ-45 connector 10 GbE |
| NIC | ConnectX-7 Smart NIC |
| Wi-Fi | WiFi 7 |
| Bluetooth | BT 5.4 |
| Audio-output | HDMI multichannel audio output |
| Display Connectors | 1x HDMI 2.1a |
| NVENC | NVDEC | 1x | 1x |
| OS | NVIDIA DGX OS |
| System Dimensions | 151 mm L x 151 mm W x 52 mm H (1.19L) |
| System Weight | 1.2 kg |
Frequently Asked Questions
Q: What is the core technology powering the MSI EdgeXpert?
A: The MSI EdgeXpert is powered by the cutting-edge NVIDIA® GB10 Grace Blackwell Superchip, delivering petaflop-scale performance for advanced AI computing.
Q: How much unified system memory does the MSI EdgeXpert include?
A: It features 128 GB LPDDR5x coherent, unified system memory, providing ample capacity for complex AI model development and experimentation.
Q: Can this supercomputer run and scale large language models (LLMs) locally?
A: Yes, the MSI EdgeXpert supports running LLMs with up to 200 billion parameters locally, and with NVIDIA ConnectX networking, two stacked systems can handle models up to 405 billion parameters.
