Powered by the latest NVIDIA RTX GPUs & Intel Xeon-W CPU. Preinstalled deep learning frameworks
- Up to 18,432 CUDA Cores, 288 RT Cores, 2,304 Tensor Cores, 192GB GPU memory
- Up to 65.2 TFLOPS Peak Single Precision Floating-Point Performance, 522TFLOPS Peak Tensor Performance
- Workflow speed-up of up to 30x
- Highly optimized cross compatible stack of data science libraries
- Deep Learning and AI-Accelerated Analytics Workloads
Maximize data science productivity gains and experience faster model development and training
As companies capture more data, powerful computing platforms with the speed and capacity to convert massive amounts of information into insights are needed so they can create better products and services for their customers. Accelerate data preparation, model training, and visualization with a new breed of workstations, the NVIDIA-powered Data Science Workstation.
AceleMax AI Workstations for Data Science are based on a powerful reference architecture made up of four, high-end NVIDIA Quadro RTX™ or GeForce RTX™ GPUs and NVIDIA CUDA-X AI™ accelerated data science software. CUDA-X AI is a collection of libraries that enable modern computing applications to benefit from NVIDIA’s GPU-accelerated computing platform. These data science workstations make it easy for scientists to wrangle, prep, train and deploy models quickly and accurately.
Built on the world’s most advanced Quadro® RTX™ GPUs, NVIDIA-powered Data Science Workstations provide GPU memory to handle the largest datasets. They include optimized data science software powered by NVIDIA CUDA-X AI, a collection of NVIDIA GPU accelerated libraries featuring RAPIDS data processing and machine learning libraries, TensorFlow, PyTorch and Caffe. The result is an integrated solution built by leading workstation partners to ensure maximum compatibility and reliability. With optional support services for NVIDIA developed software, it’s everything you need to boost productivity, enjoy faster time to insight, and lower the cost of your data science projects.
Single LGA2066 socket Intel® Xeon® W-Series processor
GPU Support & Quantity
4x NVIDIA Quadro RTX 8000, 6000, 5000, 4000 / 4x NVIDIA GeForce RTX 3090 ti, 30980 ti / 4x NVIDIA A6000
Intel® C422 chipset
System Memory (Maximum)
- 8x DDR4 DIMM slots
- Quad Channel DDR4 Memory Architecture
- Supports DDR4 RDIMM and LRDIMM, Max. 512GB
PCIe 3.0 x16
2 x 10 Gigabit LAN, Intel® X550-AT2
Supports Out-of-band remote management and In-band Control Center
• 2 x 5.25”
• 4 x 2.5”
• 2 x Combo 3.5”/2.5”
• 2 x M.2 Socket 3
• 2 x U.2 connectors
1600W 80 PLUS Gold certified PSU
16.3” x 13” x 18” / 415mm x 332mm x 458mm (H x W x D)
Optimized for Turnkey Solutions
Enable powerful design, training, and visualization with built-in software tools including TensorFlow, Caffe, Torch, Theano, BIDMach cuDNN, NVIDIA CUDA Toolkit and NVIDIA DIGITS.