DASH_Box
DASH built a local compute box to enable our faculty to experiment and apply AI capabilities rapidly. While Northeastern University is a leader in AI research and has amazing computing resources, with over 50,000 CPU cores and over 500 GPUs in our Discovery compute cluster, research can often be jump-started with just a fraction of this hardware. That's where the DASH_Box comes in. A desktop with supercharged RAM and a GPU. It's bigger and more powerful than what most people have on their laptops or desktops, and it's less complicated than the cloud.
This local computing solution is designed for usability and puts powerful AI capabilities at your fingertips. Whether you're fine-tuning models, running experiments, or testing new ideas, the DASH Box makes high-performance computing faster, more accessible, and seamlessly integrated into your workflow. It's not about replacing large-scale infrastructure; it's about making AI research more efficient, one breakthrough at a time.
For researchers looking to push the boundaries of AI, the DASH_Box isn't just a tool; it's a catalyst for discovery.
Faculty case studies
Under the hood
The DASH team has developed a high-performance computing resource for advanced machine learning, deep learning, and dataintensive applications to accelerate AI-driven research and education. The DASH_Box provides on-demand computational capability, featuring:
- PROCESSOR: AMD Ryzen 7950X (16 cores, 32 threads)
- MEMORY: 128GB DDR5 Ripjaws RAM for high-speed data processing
- GPU: NVIDIA RTX A6000 with 48GB VRAM, 10752 CUDA cores, and 336 Tensor cores for accelerated AI workloads
This desktop machine balances raw processing power with maximum flexibility, making it ideal for researchers working with large-scale neural networks, LLM inference, and AI modeling.
Want to dive in?
D'Amore-McKim faculty with an interest in using DASH_Box should contact us for details.
