Malaysia’s First NVIDIA Powered DGX SPARK

AI Supercomputing Lab for Education & Innovation

AI Supercomputing Lab for Education & Innovation

Powered by NVIDIA Supercomputers

APU is establishing a next-generation AI Supercomputing Lab with a cluster of NVIDIA DGX Sparks Units designed to provide students with access to cutting-edge AI infrastructure typically found only in major research centres and technology companies.

Next-Generation AI Architecture

Each DGX Spark unit is powered by the NVIDIA GB10 Grace Blackwell Superchip featuring 128 GB LPDDR5x unified memory allowing students and researchers to run, train, and fine-tune Large Language Models (LLMs) with up to 200 billion parameters locally.

Ultra-High AI Computing Performance

Each machine provides up to 1 PetaFLOP of AI performance, enabling rapid processing of complex AI algorithms, deep neural networks, and large-scale data analysis.

Real Hands-on AI Experience

Through this AI Supercomputing Lab, APU aims to empower students with real-world experience in advanced artificial intelligence development, preparing graduates to lead the next generation of AI-driven innovation and technological transformation.

NVIDIA GB10
Grace Blackwell Superchip

Advanced
AI Architecture

128GB
Unified Memory

Massive LLM
Capacity

Up to
1 PetaFLOP Performance

Extreme
AI Power

Compact &
Energy Efficient

Green AI
Technology

All NVIDIA® logos and product names, including NVIDIA DGX™ and NVIDIA Spark™, are trademarks of NVIDIA Corporation.

The NVIDIA DGX Spark is also adopted by top universities such as Stanford, Harvard, Arizona State University, Mississippi State University, and the University of Delaware. Details from Nvidia Blog : https://blogs.nvidia.com/blog/dgx-spark-higher-education/

APU AI Supercomputing Lab

APU has launched Malaysia’s first AI Supercomputing Lab powered by NVIDIA DGX Spark, officiated by YB Dato' Seri Diraja Dr Zambry bin Abdul Kadir, Minister of Higher Education.

The lab provides students, academics and researchers with advanced computing infrastructure for Large Language Models (LLMs), Generative AI, Machine Learning, Data Science, Intelligent Engineering and Agentic AI.

Each NVIDIA DGX Spark supports AI models of up to 200 billion parameters locally, enabling users to develop, experiment with and test AI models within the university.

Students gain hands-on experience in dataset preparation, model fine-tuning, performance evaluation and AI application development. The lab also supports teaching, final-year projects, postgraduate research and interdisciplinary projects across AI, Computer Science, Data Science, Software Engineering, Computer Engineering, Mechatronic Engineering and Quantum Computing.

Through this infrastructure, APU enables its academic community to develop, test and advance AI solutions, strengthening practical learning and research in emerging AI technologies.