AMD Ryzen 9000 Series (16 Cores)
Up to 2x NVIDIA RTX 5090, RTX PRO 6000 Blackwell
Up to 192 GB DDR5 Memory
GPU: Air-cooling | CPU: Water-cooling
AMD Threadripper PRO 7000WX/9000WX (96 Cores)
Up to 2x NVIDIA RTX 5090 or 4x RTX PRO 6000 Blackwell
Up to 1 TB DDR5 Memory
GPU: Air-cooling | CPU: Water-cooling
Optimized for stable diffusion, LLaMA, Alpaca. ChatGPT-like AI On Your Local Computer
AMD Threadripper Pro (96 Cores)
Up to 7x Water-cooled NVIDIA 5090, A100, H100, H200, RTX PRO 6000 Blackwell
Up to 1 TB DDR5 Memory
Enterprise-class water-cooling
Up to 3x times lower noise vs. air-cooling. Maximum GPU power for inference and training
Intel Core i9 14900K (24 Cores)
Up to 2x NVIDIA RTX 5090, RTX PRO 6000 Blackwell
Up to 192 GB DDR5 Memory
GPU: Air-cooling | CPU: Water-cooling
Intel Xeon W-2500/W-3500 (60 Cores)
Up to 2x NVIDIA RTX 5090 or 4x RTX PRO 6000 Blackwell
Up to 2TB DDR5 Memory
GPU: Air-cooling | CPU: Water-cooling
NVIDIA AI Workstation for AI Research
Intel Xeon W-2500/3500 (60 Cores)
Up to 6x NVIDIA RTX 5090, RTX PRO 6000 Blackwell, A100, H100, H200
Up to 2TB DDR5
Professional-grade Water-cooling
Up to 3x times lower noise vs. air-cooling. Simple maintenance
AMD Threadripper Pro (96 Cores)
Up to 7x Water-cooled NVIDIA 5090, A100, H100, H200, RTX PRO 6000 Blackwell
Up to 1 TB DDR5 Memory
Enterprise-class water-cooling
Up to 3x times lower noise vs. air-cooling. Maximum GPU power for inference and training
2x AMD EPYC 9004, 9005 (384 Cores)
Up to 3x NVIDIA A100, H100, H200, RTX 5090 or 3x RTX PRO 6000 Blackwell
Up to 8 TB DDR5 Memory
Enterprise-class water-cooling
2x Intel Xeon 4th/5th Gen (128 Cores)
Up to 5x NVIDIA RTX 5090, RTX PRO 6000 Blackwell, A100, H100
Up to 4 TB
Professional-grade water-cooling
NVIDIA RTX data science workstations come pre-installed with frameworks for deep learning such as Tensorflow, Torch/PyTorch, Keras, Caffe 2.0 Caffe-nv, RAPIDS, Docker, Anaconda, MXnet, Theano, CUDA, and cuDNN. Our BIZON Z-Stack Tool has a user-friendly interface for easy framework installations and upgrades. If a new version of any framework is released, you can upgrade with a click of a button, avoiding complicated command lines.
All tested and tuned to work together immediately with no additional setup.
We offer a warranty of up to 5 years for labor & up to 3 years for parts replacement.
Our technical support staff is highly knowledgeable in deep learning frameworks.
Should a part go bad, we offer an advanced replacement option to reduce downtime.
We offer up to 1-3 days on most models by keeping inventory and maintaining direct connections with distributors.
Ships within 1-3 days. Shipping worldwide. Overnight US shipping available.
Unsure what to get? Have technical questions?
Contact us and we'll help you design a custom system which will meet your needs.