【Pre-Order】Lenovo ThinkStation PGX – NVIDIA GB10 Super Chip/128GB/4TB/NVIDIA DGX OS (30KL0003HK)
HK$35,200
Before placing order, please contact us to learn about lead time
Personal AI Workstation
Introducing the ThinkStation PGX, a Lenovo workstation based on the NVIDIA® GB10 Grace Blackwell Superchip that achieves petaflop AI compute power. It provides powerful support to complement your AI systems built from the data center, revolutionizing your AI development and achieving unprecedented results. The ThinkStation PGX is ideal for AI researchers and developers, data scientists, practitioners, students, and application engineers.
NVIDIA GB10 Grace Blackwell Superchip
128GB Unified Memory Architecture
NVIDIA DGX Operating System and NVIDIA AI Software Stack
Supports large-scale generative AI models with up to 200 billion parameters
For even more computing power, developers can interconnect two ThinkStation PGX servers to support even larger AI models with up to 405 billion parameters
The Lenovo ThinkStation PGX small form factor, powered by the NVIDIA GB10 Grace Blackwell Superchip, enables simplified AI workflows right at your desk. It comes preloaded with the NVIDIA AI software stack and seamlessly integrates with your workstation for on-device AI development, eliminating the complexity and cost of cloud-based solutions.
Seamless Integration Into AI Pipelines
An advanced NVIDIA Blackwell GPU supports complex AI workflows, including fine-tuning, inference, and data processing, with features designed to streamline deep learning, computer vision, and generative AI development.
Endless Possibilities With Smarter Memory Solutions
The compact ThinkStation PGX workstation offers exceptional unified memory and bandwidth for its size and price point. Effortlessly fine-tune, prototype, and test large AI models locally, while experiencing faster iterations, reduced complexity, and enhanced productivity.
Dual-System Connectivity for More Potential
With the ConnectX®-7 networking port, combine the power of two ThinkStation PGX devices to work with even larger AI models and unlock new possibilities for advanced AI innovations.
Big Models, Small Chip, Limitless Potential
The NVIDIA GB10 Grace Blackwell Superchip combines cutting-edge graphics with a powerful multicore ARM CPU to deliver an energy efficient system-on-a-chip (SOC) solution. It’s built to handle complex AI tasks and massive datasets with incredible speed and efficiency, making it perfect for tackling demanding workloads locally.
Ready-to Go AI Development Environment
A compact entry point to advanced AI, the ThinkStation PGX is preloaded with the NVIDIA DGX™ OS and NVIDIA AI software stack, providing an optimized space for AI model development. With tools like PyTorch and Jupyter® Notebooks, engineers can easily prototype, fine-tune, and inference models for smooth deployment to data center or cloud platforms.
Your AI Playground: Experiment. Build. Succeed.
The ThinkStation PGX workstation offers developers a secure sandbox for prototyping AI models, freeing up cluster resources for production workloads. This streamlines workflows, keeps IP on-premises, and reduces security risks — ideal for experimentation without compromising enterprise standards.
Ports & Slots
1 Power button
2 4 x USB-C® (USB 20Gbps)
3 HDMI® 2.1a (supports resolution up to 4K@60Hz)
4 Ethernet (RJ45)
5 ConnectX®-7 Smart NIC
Additional information
Processor
Built into NVIDIA® GB10 Grace Blackwell Superchip, 20 core Arm, 10x Cortex-X925 + 10x Cortex-A725
Memory
128GB LPDDR5x, 256-bit, Unified System Memory
PCIe NVMe Drive
4TB M.2 NVME SSD with elf-encryption
Chipset
NVIDIA® GB10 Grace Blackwell Superchip
Integrated Graphics
NVIDIA® Blackwell Architecture, Built into NVIDIA GB10 Grace Blackwell Superchip
Rear Ports
. 1x USB-C® (USB 20Gbps / USB4®), with USB PD 3.1 in and DisplayPort™ 2.1
. 2x QSFP (200Gbps each, for connecting two ThinkStation® PGX units)
. 3x USB-C® (USB4® 20Gbps), with DisplayPort™ 2.1
. 1x HDMI®
. 1x Ethernet (10GbE RJ-45)
We will strive to arrange shipment/pickup within the timeframe indicated (5-7 days, 1-3 weeks, 4-6 weeks, etc.). If there’s no timeframe indicated, please contact us before placing an order.
For more details on delivery/pickup, please visit FAQs.
