Estimated Shipping Date: 1-3 business days
Product Information
Powered by the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip and 748GB of large coherent memory, the MSI XpertStation WS300T60L on NVIDIA DGX Station™ architecture delivers data-center-class performance for AI training, inference, and simulation workloads, right from your deskside.
Overview
- Tower (NVIDIA DGX Station™)
- Single NVIDIA Grace™ CPU Superchip with 72 Arm® Neoverse V2 cores
- Single NVIDIA Blackwell Ultra GPU (RTX PRO 2000, 4000, 4500, 5000, or NVIDIA RTX Pro 6000 Max-Q)
- 748 GB of Coherent Memory
- Two 2280 PCIe 5.0 x4 NVMe M.2 ports (Filled with a 2TB RAID1, connected to the CPU)
- Two 2280 PCIe 6.0 x4 NVMe M.2 ports (Open and available for expansion, connected to the CX8)
- Ubuntu 24.04 LTS with Nvidia AI Developer Tools pre-installed
- Three PCIe 5.0 expansion slots
- Two QSFP112 400G Ethernet ports from integrated NVIDIA ConnectX-8 SuperNIC
- One 1000Base-T Dedicated Server Management Port with:
- ASPEED AST2600 with IPMI 2.0 & DMTF Redfish Support
- Hardware Root of Trust & TPM 2.0 Supported
What Sets MSI XpertStation WS300 Apart
Compute-Dense Architecture
The NVIDIA DGX GB300 workstation combines high-performance NVIDIA Grace CPU and NVIDIA GB300 Blackwell Ultra GPU through the NVIDIA® NVLink® Chip-to-Chip (C2C) interconnect, delivering exceptional compute density and efficient system communication.High-Speed Networking
NVIDIA ConnectX®-8 SuperNIC™ in the NVIDIA DGX GB300 Station delivers up to 800Gb/s of low-latency, high-bandwidth connectivity, enabling fast data transfer and scalable performance for large-scale AI workloads.Large Coherent Memory
A 748GB coherent memory pool in the MSI WS300T60L GB300 DGX Station combines 252GB of high-speed HBM3e GPU memory and 496GB of LPDDR5X system memory through the C2C interconnect, enabling faster data access and efficient large-scale AI model training.End-to-End AI Software Support
The NVIDIA DGX workstation AI Software Stack provides an end-to-end solution for AI workloads including fine-tuning, inference, and data science, enabling seamless development and deployment from desktop to data center.Accelerating Every AI Workload
The MSI XpertStation WS300 with the GB300 superchip on NVIDIA DGX Station™ architecture excels at agentic AI because it combines 748GB of coherent unified memory with 20 petaFLOPS of FP4 compute, allowing it to handle massive KV caches, multi-step reasoning, and hundreds of concurrent autonomous agents locally. It is perfect for Frontier LLM model development, data science, and autonomous AI agents with NVIDIA OpenShell. Launch hundreds of parallel AI agents simultaneously without cloud serialization delays on large foundation models up to 1 trillion parameters using the MSI WS300 NVIDIA GB300 DGX workstation.
AI Development
With the MSI WS300T60L NVIDIA GB300 station, accelerate deep learning and machine learning training for AI applications ranging from predictive maintenance and medical imaging analysis to natural language processing.
Data Science
With the MSI WS300T60L NVIDIA DGX workstation, expedite end-to-end data science workflows to enable faster data ingestion, analysis, and insight generation across massive datasets.
AI Inference
The MSI Xpertstation WS300 NVIDIA GB300 workstation accelerates LLM token generation by combining massive unified coherent memory with high-bandwidth NVLink-C2C and native FP4 tensor core acceleration. See your local inference for large and complex AI models skyrocket with the MSI NVIDIA DGX GB300 workstation, delivering high-speed performance for LLM token generation, data analysis, content creation, and AI chatbots.
Personal Cloud
With the MSI XpertStation WS300 GB300 DGX Station™, run advanced AI models on local data and serve as a centralized compute node for team-based fine-tuning and on-demand deployment.
MSI XpertStation WS300 NVIDIA DGX GB300 workstation Features:
- 245mm (9.6") Wx 528.4mm (20.8") Hx 595mm (23.4") D
- up to one NVIDIA RTX PRO 6000 96GB Workstation - 600W
- CPU Memory Up to 496GB LPDDR5X | Up to 396GB/s GPU Memory Up to 252GB HBM3e | 7.1TB/s
- One 10 GbE RJ45 port (Marvell AQC113) (2) 400 GbE QSFP ports (NVIDIA ConnectX®-8)
- Two 2280 PCIe 5.0 x2 NVMe M.2 ports (from CPU) (2) 2280 PCIe 6.0 x4 NVMe M.2 ports (for training data)
- One Double-Wide PCIe 5.0 x16 slot for display (2) Single-Wide PCIe 5.0 x16 slots (each with x8 signal only) (1) PCIe x1 2232 M.2 for WiFi/Bluetooth card
- Qualified BMC module from Aspeed AST2600 BMC
- 1600W 80 PLUS Titanium ATX PSU
