1-888-577-6775 sales@bizon-tech.com
Need Help?
Login / Register
0
  1. Home
  2. AI, Deep Learning and HPC Servers
  3. Water-cooled GPU Servers

Water-cooled GPU Servers

GPU Servers for deep learning, AI research and HPC
Cooling type: Water-cooling
8 GPU, 10 GPU Servers, GPU Systems. Maximum Acceleration and Cost Efficiency for AI / Deep Learning and HPC Applications.
  1. BIZON Z9000 – Liquid cooled NVIDIA Quadro RTX Deep Learning, AI and Parallel Computing GPU Server – Up to 10 GPU, dual Xeon up to 56 cores
    BIZON Z9000 – Liquid cooled NVIDIA Quadro RTX Deep Learning, AI and Parallel Computing GPU Server – Up to 10 GPU, dual Xeon up to 56 cores
    Starting at $32,990 In Stock
    Customize
    Liquid cooled 10 x TITAN RTX Deep Learning, AI or Rendering Rackmount Server.

    The World's First

    Preinstalled TensorFlow, Keras, PyTorch, Caffe, Caffe 2, Theano, CUDA, and cuDNN.
    • Custom liquid cooling system (Dual CPUs and 8-10 x GPUs)
    • Up to 3X times higher performance vs. air cooled TITAN RTXs (no overheating).
    • Low temperatures (59C vs 90C for air-cooled server).
    • 35% lower noise level (59dB vs 90dB; motorcycle engine running is about 90 dB). You can place server in lab/office.
    • 24/7/365 operation at 100% load.
    • Dual Intel Xeon Silver, Gold or Platinum (up to 56-Cores).
    • Up to 10 x liquid-cooled NVIDIA Quadro RTX.
    • Up to 5 x NVLinks
    • DDR4 2666 MHz or 2933 MHz ECC Memory (up to 6 TB)
    • PCIe SSD or HDDs for storage.
    • Rackmountable server chassis with redundant power supply.
  2. BIZON ZX9000 – Liquid-cooled NVIDIA Quadro RTX Deep Learning, AI and Parallel Computing GPU Server – Up to 10 GPU, Dual AMD EPYC up to 128 cores
    BIZON ZX9000 – Liquid-cooled NVIDIA Quadro RTX Deep Learning, AI and Parallel Computing GPU Server – Up to 10 GPU, Dual AMD EPYC up to 128 cores
    Starting at $34,990 In Stock
    Customize
    Liquid-cooled AMD EPYC + 10 GPU Deep Learning, AI or Rendering Rackmount Server.

    The World's First

    Preinstalled TensorFlow, Keras, PyTorch, Caffe, Caffe 2, Theano, CUDA, and cuDNN.
    • Custom liquid cooling system (Dual AMD EPYC CPUs and 8-10 x GPUs)
    • Up to 3X times higher performance vs. air cooled TITAN RTXs (no overheating).
    • Low temperatures (59C vs 90C for air-cooled server).
    • 35% lower noise level (59dB vs 90dB; motorcycle engine running is about 90 dB). You can place server in lab/office.
    • 24/7/365 operation at 100% load.
    • Dual AMD EPYC 7252 series Processors (up to 128 cores).
    • Up to 10 x liquid-cooled NVIDIA Quadro RTX GPUs.
    • Up to 5 x NVLinks
    • DDR4 3200 MHz ECC Memory (up to 8 TB).
    • PCIe SSD or HDDs for storage.
    • Rackmountable server chassis with redundant power supply.