shopify analytics ecommerce

NVIDIA Tesla V100 Front

More Views

NVIDIA Tesla V100 Passive GPU

The NVIDIA® Tesla® based on the industry leading Volta Architecture is currently the most advanced data centre GPU ever built. Specifically designed to accelerate AI, HPC, and Graphics this GPU is the driving force allowing data scientists, researchers, and engineers to tackle challenges once thought of as impossible.

Price as configured: £0.00 Excl. VAT


Price as configured (excl. VAT): £0.00


* Required Fields

Price as configured (excl. VAT): £0.00



We are now gathering more and more data on ourselves and the world around us. By studying this data and obtaining insights hidden away we are unlocking the possibilities to change the world, enabling new fields such as personalised cancer therapy, improve virtual personal assistants ability to understand and converse with us and monitor and predict Mother Nature to give warning of the next big natural disaster.

The NVIDIA® Tesla® V100 is currently the most complex and powerful Data centre GPU ever conceived and is the driving force for the new revolution in AI, HPC and graphics workflows. Based on the new NVIDIA Volta architecture platform with 5120 CUDA Cores and now with options for both 16GB and 32GB of HBM2 Graphical Memory. The Tesla V100 has compute capabilities researchers and analysists previously could only dream of.

Artificial Intelligence Training & Inference

Artificial Intelligence is becoming more common in our lives from virtual private assistants to autonomous cars and the trend is not only set to continue but accelerate in the coming years. The NVIDIA® Tesla® V100 is at the forefront of these ground breaking new industries and is providing data scientists the platform to turn their visions into reality.

To solve these kinds of problems neural networks require deep learning training, a highly compute intensive process that are only getting exponentially more complex however, still need to be completed in a realistic timeframe. The NVIDIA® Tesla® V100 with its 5120 CUDA Cores and 640 dedicated Tensor Cores is the first GPU to produce over 100 TeraFLOPS of deep learning performance. Plus, NVLINK enables 2 of these cards to share memory resources, effectively doubling your Graphical memory available and delivering up to 300GB/s memory bandwidth. AI models that previously took weeks or months to complete can now be performed in a matter of days.

Once your AI system is fully trained or if you want to expand upon an existing system then the NVIDIA® Tesla® V100 is purposely designed to provide the maximum performance possible to a hyperscale server rack. This provides up to 47x higher inference performance over a CPU only server empowering users to scale-out their AI services to levels previously impractical.

High Performance Computing

The NVIDIA® Tesla® V100 not only excels in AI workflows it is also a powerful tool for High Performance Compute (HPC) users. From predicting weather patterns, to breakthroughs in medical science or revolutionising energy sources. Our data scientists rely daily on GPU compute cards to accelerate their simulations. AI is one way scientists are further developing on top of these simulation techniques and the Tesla® V100 is the perfect tool to marry these techniques together.

NVIDIA® CUDA® Cores: 5120
Peak Double Precision Floating Point Performance: 7 Tflops (GPU Boost Clocks)
Peak Single Precision Floating Point Performance: 14 Tflops (GPU Boost Clocks)
Deep Learning (Tensor) TFLOPS: 112 Tflops (GPU Boost Clocks)
Capacity: 16 or 32 GB HBM2
Memory Interface: 4096-bit
Memory Bandwidth: 900 GB/s 
Bus Type: PCI-Express 3.0 x16
Thermal Solution: Passive
250 W
1 × 8-pin CPU power connectors

Write Your Own Review

You're reviewing: NVIDIA Tesla V100 Passive GPU

How do you rate this product? *

  1 star 2 stars 3 stars 4 stars 5 stars
Build Quality
Turnaround Time
Likely To Recommend
Overall Experience

NVIDIA Tesla V100 Passive GPU