Language :
COMPUTEX 2025 is just around the corner. AI leader Leadtek Research Inc. will be exhibiting the latest NVIDIA RTX PRO 6000 Blackwell GPUs and NVIDIA DGX Spark at Booth #S0407a, 4F, Hall 2, Nangang Exhibition Center. In addition, Leadtek will host a GPU-Accelerated AI Pavilion in the InnoVEX area, collaborating with innovative startups to demonstrate Physical AI Digital Twins and On-Premises AI Agent solutions—highlighting how enterprises can rapidly adopt AI to create real value.
Image: From left to right, NVIDIA RTX PRO 6000 Blackwell Server Edition, NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, NVIDIA RTX PRO 6000 Blackwell Workstation Edition
The highlight of Leadtek's exhibition is undoubtedly the ultra-high-end NVIDIA RTX PRO 6000 Blackwell series GPUs, based on the new Blackwell architecture and featuring fifth-generation Tensor Cores that deliver up to 3× the performance of the previous generation, with added support for FP4 precision and DLSS 4 Multi Frame Generation technology, enabling flexible AI model development.
Importantly, the NVIDIA RTX PRO 6000 Blackwell Server Edition, NVIDIA RTX PRO 6000 Blackwell Workstation Edition GPU and NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition GPU are all equipped with 96GB GDDR7 ECC memory. The RTX PRO 6000 Max-Q variant enables dense 4x GPU configurations, which can provide 384GB of GPU memory in a single workstation right at your desk. Whether for developing large language models (LLMs), AI agents, or industrial and physical AI applications via NVIDIA Omniverse, these configurations unleash the full potential of the AI era—driving innovation and breakthroughs.
DGX Spark is the world's smallest AI supercomputer, empowering millions of researchers, data scientists, robotics developers and students to push the boundaries of generative and physical AI with massive performance and capabilities.
Powered by the NVIDIA GB10 Grace Blackwell Superchip, DGX Spark delivers up to 1,000 AI TOPS of AI performance within a compact 150 x 150 x 50.5 mm compact form factor. Equipped with 128 GB of memory and pre-installed with the NVIDIA AI software stack, DGX Spark supports AI models with up to 200 billion parameters. It's ideal for prototyping, fine-tuning, and inference of the latest generation AI models, and can be seamlessly deployed to data centers or the cloud. Additionally, with built-in NVIDIA ConnectX networking, two DGX Spark systems can be connected to handle AI models with up to 405 billion parameters.
Image: NVIDIA DGX™ Spark
Leadtek is launching the WS650 Mini AI Workstation, available in both air-cooled and liquid-cooled versions.
Air-Cooled WS650
Liquid-Cooled WS650L
For compute-intensive tasks, Leadtek offers NVIDIA-Certified Systems:
Addressing growing enterprise concerns about cybersecurity, Leadtek also presents Zero Trust Endpoint Devices based on PCoIP Zero Clients, ensuring security and regulatory compliance through a “never trust, always verify” approach.
Image: WinFast WS650 Mini AI Workstation
Leadtek partners with startups to offer an immersive AI application experience at the booth. One of the exciting demos features digital twin applications developed on NVIDIA Omniverse libraries, transforming factory automation and robot training, while drastically accelerating industrial design, validation, and optimization. Additionally, the driving behavior analysis system using AIDMS highlights the flexibility and fast adoption potential of AI in real-world applications.
“AI is not the future—it's happening now.”
Visit Leadtek at Booth #S0407a at COMPUTEX 2025 to explore the possibilities of enterprise digital transformation.
Leadtek Official Website: www.leadtek.com.tw
About COMPUTEX 2025:
Date: May 20 (Tuesday) to May 23 (Friday), 2025
Venue: Taipei Nangang Exhibition Center Hall 2, 4th Floor
Booth Number: S0407a
Time: 9:30 AM – 5:30 PM
Future
