BIZON Z8000 – Dual Xeon Liquid-cooled NVIDIA RTX 3090, 2080 Ti, TITAN RTX Deep Learning and GPU Rendering Workstation PC – Up to 7 GPU, up to 56 cores

Z8000

7 x GPU Deep Learning, Rendering Workstation with FULL Liquid Cooling

FULL CUSTOM WATER COOLING FOR CPU AND GPU. Up to 30% lower noise level vs air-cooling.
Plug-and-Play Deep learning Workstations designed for your office. Multi GPU rendering PC. Powered by latest NVIDIA GPUs, preinstalled deep learning frameworks.
Estimated Ship Date: 3-7 Days

Starting at $19,990

System Core
 Processors – Liquid cooled (Intel Xeon Scalable; 2nd Generation)

Processors – Liquid cooled (Intel Xeon Scalable; 2nd Generation)

  • Silver

  • Gold

  • Platinum

Motherboard

Motherboard

Liquid Cooling

Liquid Cooling

Custom liquid cooling system: Up to 20% lower noise vs. air cooling (49 dB for water cooling vs. 62 dB for air cooling on maximum load).
It's well known that most of the noise generated by GPUs (especially when we talk about 4 x blower fan GPUs). Our handcrafted water cooling system includes 2 x 360mm radiators, a high-pressure water pump, a reservoir, a CPU water block, 4 x GPU water blocks, and hard tubes. It takes 3 full days for assembling by water cooling expert.
CollapseLearn More
Memory

Memory

Below are recommendations for choosing RAM size.

A Deep Learning computer should have at least as much RAM as GPU memory.

  • 2 x NVIDIA 2080 Ti GPUs: 32 GB (2 x 11 GB of 2080 Ti's memory = 22 GB minimum).
  • 4 x NVIDIA 2080 Ti GPUs: 64 GB (4 x 11 GB of 2080 Ti's memory = 44 GB minimum).
  • If you are working with large images we recommend you 128 GB of memory.
CollapseLearn More
Operating System

Operating System

You can choose multiple operating systems.
  • BIZON Z–Stack (includes Ubuntu 18.04 and latest deep learning frameworks)
    Recommended for Deep Learning. Preinstalled with the Most Powerful Deep Learning Software (including Tensorflow, Torch/PyTorch, Keras, Caffe 2.0 Caffe-nv, Theano, CUDA and cuDNN). We provide BIZON Z-Stack Tool with a user-friendly interface for easy installation and future upgrades. If a new version of any framework is released, you can upgrade with a click of a button and avoid complicated command lines.

  • Windows 10 Pro
    Operating system for wide range of tasks.

CollapseLearn More
Graphics
GPU Support

GPU Support

Make sure to choose the GPU option that will match the GPU amount. If you order 7 GPU-Ready system, make sure to order 7 GPUs (the same for 2 GPU-Ready and 4 GPU-ready). Due to the complexity of the liquid-cooling loop, you will not be able to add extra GPUs by yourself.
CollapseLearn More
Graphics Card

Graphics Card

GPUs comparison:
  • RTX 2080 8 GB: base line. (10.1 TFLOPS).
    NVIDIA Turing Architecture.

  • RTX 3070 8 GB: up to +30% performance (20.3 TFLOPS).
    Latest NVIDIA Ampere Architecture.

  • RTX 3080 10 GB: up to +40-50% performance (29.8 TFLOPS).
    Recommended for most use cases. Best GPU for deep learning in 2020-2021. Latest NVIDIA Ampere Architecture.

  • RTX 3090 24 GB: up to +60-70% performance (35.6 TFLOPS)
    Recommended for training with large batch sizes and large networks.
    Latest NVIDIA Ampere Architecture.

  • RTX 2080 Ti 11 GB: up to +20-30% performance (13.4 TFLOPS).
    Best GPU for deep learning in 2019. NVIDIA Turing Architecture.

  • Titan RTX 24 GB: up to +40% performance (16.2 TFLOPS)

* TFLOPS numbers are for FP32 performance (the standard precision for deep learning training).
CollapseLearn More
  • NVIDIA GeForce 30-Series

  • NVIDIA GeForce 20-Series

  • NVIDIA Quadro

NVIDIA NVLink Bridge

NVIDIA NVLink Bridge

  • NVLink is a high-speed interconnect designed to allow multiple video cards (GPUs) to communicate directly with each other.
  • We have seen up to +15% performance increase when using NVLink with 2 x NVIDIA Quadro RTX (TensorFlow) compared to the same setup without NVLink.
  • Each additional NVLink will add up to +5% performance.
  • Example: For 4 GPUs you will get up to +20% performance. Numbers are for reference only and may vary depending on many factors.
  • One NVLink per 2 GPUs. NVLink is optional.
  • Performance increase and NVLINK support depend on software support. Some application does not have NVLink support and you won't see any performance difference. Check with the developers of your application if they have implemented or plan to add NVLink support.
CollapseLearn More
Storage
HDD #1 (Operating System, Applications)

HDD #1 (Operating System, Applications)

HDD #2

HDD #2

HDD #3

HDD #3

HDD #4

HDD #4

Additional hard drives

Additional hard drives

Optional storage drive for footage, scratch files, media cache or project files. SSD for project files, scratch, & media cache.
CollapseLearn More
RAID Controller

RAID Controller

  • RAID controller for PCIe NVMe SSDs

  • RAID controller for hard drivers and SATA SSDs

Adapters
Additional Controllers

Additional Controllers

Peripherals
Peripherals

Peripherals

UPS System

UPS System

Service & Support
Type of chassis

Type of chassis

Service & Support

Service & Support

The "Life-time Expert Customer Care with 3 / 4 / 5 Year Limited Warranty" includes the following benefits:

  • Life-time access to our expert customer support team for all kinds of computer issues.

  • Three / four / five years (depending on the option you choose) of labor free warranty service (including labor costs for part replacements, and diagnostics).

  • One / two / three years (depending on the option you choose) of direct defective part replacement service directly from BIZON's inventory.
CollapseLearn More

Need help?

Contact our specialists and get help.

Ask a Question
Personal AI Supercomputer at your Desk
Plug-and-Play Deep learning, Rendering Workstations designed for your office. Powered by latest NVIDIA GPUs, and liquid cooling.
Ports

Front panel:

2x USB 3.0, Mic, Headphone, Reset, Power button

Rear panel:

    • 1 x PS/2 Mouse/Keyboard combo port
    • 1 x USB 3.1 Gen 2 Type-C
    • 1 x USB 3.1 Gen 2 Type-A
    • 4 x USB 3.1 Gen 1
    • 4 x USB 2.0
    • 2 x RJ45
    • 1 x USB BIOS Flashback button
    • 1 x Optical S/PDIF out
    • 5 x Audio jacks
Motherboard

ASUS WS C621E SAGE

  • Dual Intel Xeon Scalable (Socket–3647) support.
  • 7 x PCI-E slots.
  • Supports 10x SATA and 2x U.2 HDD/SSD, M.2 SSD
  • Intel C621 chipset.
CPU
Dual Intel Xeon Scalable processors with up to 28 Cores (per CPU)
RAM

  • Up to 1536 GB DDR4 2666 MHz or 2933 MHz ECC Buffered
  • 12 RAM slots.

Note: actual RAM clock speed depends on the CPU specifications and may vary.

Expansion Slots
  • 3 x PCIe 3.0 x16 (x16 mode)
  • 2 x PCIe 3.0 x16 (Single at x16, dual at x8/x8)
  • 2 x PCIe 3.0 x16 (x8 mode)
  • 1 x PCI-Express M.2
Storage

Intel C621 Chipset:

  • 8 x SATA 6Gb/s port(s)
  • Support Raid 0, 1, 5, 10

ASMedia SATA 6Gb/s controller:

  • 2 x SATA 6Gb/s port(s)
  • 4 x U.2 connector
  • 1 x M.2 Socket 3, with M Key, type 2242/2260/2280/22110 storage devices support (both SATA & PCIE mode)

Graphics Card
4 GPU-Ready: Up to 4 NVIDIA RTX/Titan cards.
7 GPU-Ready: Up to 7 NVIDIA RTX 2080, 2080 Ti cards.
Make sure to choose the GPU option that will match the GPU amount. If you order 7 GPU-Ready system, make sure to order 7 GPUs (the same for 2 GPU-Ready and 4 GPU-ready). Due to the complexity of the liquid-cooling loop, you will not be able to add extra GPUs by yourself.

Available options:

  • Nvidia RTX 2080Ti 11Gb (3 DP, HDMI, USB Type-C)
  • NVIDIA TITAN RTX 24 Gb (3 DP, HDMI, USB Type-C)
  • Nvidia RTX 3080 10 Gb (3 DP, HDMI)
  • Nvidia RTX 3090 24 Gb (3 DP, HDMI)

Display Support (all cards):
Maximum Digital Resolution: 7680x4320 @60Hz
Multi Monitor Support: 4

Onboard Audio
7.1 Channels Realtek ALC S1220A

Note: Due to limitation in HDA bandwidth, 32-Bit/192kHz is not supported for 8-channel audio. 32-Bit/192kHz is only available under Windows 10.

Onboard LAN
  • 2 x Gigabit Ethernet (Intel I210-AT)
  • 10 Gigabit Dual Port Ethernet Intel (optional)
Wireless

Wi-Fi

  • Intel 802.11ac WiFi Module
  • Supports IEEE 802.11a/b/g/n/ac
  • Supports high speed wireless connections up to 1200Mbps

Bluetooth

  • Bluetooth 4.2
Case

Cooler Master Cosmos High-End Case with advanced soundproof.

Case Drive Bays:

  • 1x 5.25in
  • 2x 2.5in
  • 2x Combo 3.5in/2.5in

7 GPU-Ready

Phanteks Enthoo Elite High-End Case with anodized aluminium panels and tempered glass sidepanel.

Case Drive Bays:

  • 1x 5.25in
  • 4x 2.5in
  • 6x 3.5in
Cooling System
  • Liquid Cooling

Full Custom Liquid Cooling system including cooling for GPUs (optional)

4 GPU-Ready system features:
  • 4 x GPU water blocks
  • 2 x 360mm Radiators
  • Water pump
  • Reservoir
    • 7 GPU-Ready system features:
      • External Cooling unit (radiators, water pump, reservoir)
      • 7 x GPU water blocks
        • Liquid cooling loop design may vary from the pictures shown on the product page, but will be of equal or better specs than what's specified above.
Power Supply
4 GPU-Ready: 1600W Power Supply
7 GPU-Ready: Dual 1600W Power Supply
Electrical and Operating Requirements
  • Line voltage: 100–240V AC
  • Frequency: 50Hz to 60Hz, single phase
  • Operating temperature: 50° to 95° F (10° to 35° C)
  • Operating Relative Humidity: 8% to 90% (non-condensing)

4 GPUs:
If you have a standard 20 A / 120V US outlet, you need one (1) 20 A /120V outlet with a dedicated circuit.
Power consumption example for 4 x NVIDIA RTX 2080 Ti:
4 x NVIDIA 2080 Ti + Dual Xeon Gold 5220 CPUs: 1400W-1500W (100% load for all the GPUs and CPUs).

7 GPUs::
If you have a standard 20 A / 120V US outlet, you can connect one power supply to one dedicated power circuit (each outlet should have its dedicated circuit). In total, you need two (2) 20 A /120V outlets with a dedicated circuit each.
Actual power consumption is not the same as maximum power supply power. Power supply power means how much watts you can get from the power supply and your actual power consumption should not be higher than max power supply power. Actual power consumption depends on your configuration (graphics card and CPU).
Power consumption example: Z8000 with 7 x NVIDIA RTX 2080 Ti + Dual Xeon Gold 5220 CPUs = 2500W-2600W (100% load for all the GPUs and CPUs).
Information for reference only. Consult your electrician for more details.
Dimensions & Weight

4 GPUs:
Case

  • Height: 35.6 inches (90.5 cm)
  • Width: 15.0 inches (38.0 cm)
  • Depth: 28.7 inches (73.0 cm)
Shipping Package
  • Height: 48 inches (121.9 cm)
  • Width: 35 inches (88.9 cm)
  • Length: 40 inches (101.6 cm)
  • Weight: 154 lbs (70.0 kg) (shipped on pallet)


7 GPUs:
Case
  • Height: 35.6 inches (90.5 cm)
  • Width: 15.0 inches (38.0 cm)
  • Depth: 28.7 inches (73.0 cm)
Cooling Unit
  • Height: 4.1 inches (10.3 cm)
  • Width: 17.3 inches (44.9 cm)
  • Depth: 22.4 inches (57.7 cm)
  • Weight: 28.7 lbs (13.0 kg)
Shipping Package
  • Height: 35.6 inches (90.5 cm)
  • Width: 22.8 inches (58.0 cm)
  • Length: 28.7 inches (73.0 cm)
  • Weight: 176-187 lbs (80.0-85.0 kg) (shipped on pallet)

Noise level and temperature

4 GPUs:

  • Idle noise level: up to 40 db
  • Idle temperature (GPUs): Average 27 C / 80.6 F (min 25 C - max 30 C)
  • Max load noise level (stress test): up to 49 db
  • Max load temperature (GPUs): Average 52 C / 125.6 F (min 50 C - max 54 C)

4 x NVIDIA TITAN RTX. Noise level measured from 6 ft / 1.8 m distance. Environment: 24 C / 75 F, 38 db. Noise meter directed to the front panel of the chassis. Temps measured after 30 min test. 120V power source. Luxmark 3.0. Ubuntu 18.04. Drivers 418. CUDA 10.0



7 GPUs:
  • Idle noise level: up to 40 db
  • Idle temperature (GPUs): Average 27 C / 80.6 F (min 25 C - max 30 C)
  • Max load noise level (stress test): up to 52 db
  • Max load temperature (GPUs): Average 55 C / 131 F (min 52 C - max 58 C)

7 x NVIDIA 2080 Ti. Noise level measured from 6 ft / 1.8 m distance. Environment: 24 C / 75 F, 38 db. Noise meter directed to the front panel of the chassis. Temps measured after 30 min test. 120V power source. Luxmark 3.0. Ubuntu 18.04. Drivers 418. CUDA 10.0

In the Box
  • Bizon Z8000.
  • Power cord (USA).
  • User manual.
  • Benchmark report.
Operating System
  • BIZON Z–Stack (Ubuntu 18.04 with preinstalled deep learning frameworks).
  • BIZON Z–Stack (Ubuntu 20.04 with preinstalled deep learning frameworks).
  • CentOS (with preinstalled deep learning frameworks) (optional).
  • Windows 10 Pro (optional).
  • Microsoft Windows Server 2019 Standard (optional).
Part Number
bizon-z8000-0719

Specifications are subject to change without notice. The entire materials provided herein are for reference only. Weight varies by configuration and manufacturing process. Power consumption, temp, noise numbers may vary +/-10%. Advertised performance is based on maximum theoretical interface values from respective Chipset vendors or organization who defined the interface specification. Actual performance may vary by system configuration. Pictures shown for the options on the configuration page are generic and for reference only.

Why Choose BIZON?

Academic Pricing and Student Discounts

BIZON offers discounts to academic institutions and students. Contact us for details.

Fast shipping. Fast built times.

Ships within 1-3 days. Shipping worldwide. Overnight US shipping available.

Money Back Guarantee

Shop with confidence.

Quality You Can Trust

Every product is tested through a rigorous quality assurance process before being shipped to you.

Expert Customers Support

Premiere customer service support with a dedicated tech support team, ready to help you.