We take cryptocurrency — so the coins you hold can buy real hardware.Pay in crypto, spend it on real hardware. Free insured shipping worldwide over $399. Plain, unbranded boxes, sent from Germany.Free insured shipping over $399. Your rate is locked for 30 minutes once checkout opens.Rate locked 30 minutes. Every item sealed, serial-checked and covered by a 24-month warranty.Sealed, 24-month warranty.

Saved items Sign in
NVIDIA Tesla V100 SXM2 module with 32 GB HBM2 passive cooler

NVIDIA

NVIDIA Tesla V100 SXM2 32 GB HBM2 graphics card

SKU CH-V6FM-RYGCE MPN V100

Data-center GPU accelerator with 32 GB HBM2 memory and SXM2 form factor for AI and HPC workloads

  • Chipset ManufacturerNVIDIA
  • GPUV100
  • Memory TypeHBM2
  • OpenGLOpenCL
  • Form FactorSXM2
  • Accelerate AI and HPC workloads with 32 GB HBM2 memory
  • High-bandwidth HBM2 memory feeds data to the GPU faster
  • Passive cooler enables dense server deployments without active fans
  • SXM2 form factor integrates directly into compatible server boards
  • Supports OpenACC, OpenCL and DirectCompute for flexible programming

Data-center AI accelerator

The NVIDIA Tesla V100 SXM2 is a GPU accelerator built for data-centre workloads such as AI training, high-performance computing and professional graphics. It delivers the compute equivalent of up to 100 CPUs in a single device. Researchers, data scientists and engineers use it to tackle problems that were previously impractical. The card carries 32 GB of HBM2 memory.

SXM2 form-factor constraints

This module uses the SXM2 form factor and a passive cooler, so it cannot be installed in a standard PCIe slot or a typical desktop chassis. It requires a server motherboard with a matching SXM2 socket and a system-level airflow solution that can dissipate the thermal load without an onboard fan. The interface also limits deployment to platforms designed for this specific mezzanine standard.

Platform compatibility checklist

Verify that your server motherboard provides an SXM2 socket and that the chassis cooling design supports passive modules of this thermal profile. Confirm the power delivery subsystem can meet the GPU's requirements. Ensure the operating system and software stack support OpenACC, OpenCL and DirectCompute APIs for the intended workloads.

Highlights

  • Accelerate AI and HPC workloads with 32 GB HBM2 memory
  • High-bandwidth HBM2 memory feeds data to the GPU faster
  • Passive cooler enables dense server deployments without active fans
  • SXM2 form factor integrates directly into compatible server boards
  • Supports OpenACC, OpenCL and DirectCompute for flexible programming

Specifications

BrandNVIDIA
Chipset ManufacturerNVIDIA
GPUV100
Memory TypeHBM2
OpenGLOpenCL
Form FactorSXM2

Questions about this item

Which capacity of the Tesla V100 SXM2 should I select?

The only capacity listed is 32 GB of HBM2 memory; there are no other versions shown in the product data.

What does the claim of 100 CPUs performance mean when the card is installed in a server?

It indicates the V100 can deliver throughput equivalent to up to 100 CPUs for AI and HPC workloads, though actual gains depend on the application and system configuration.

What does the SXM2 form factor limit in practice?

SXM2 requires a compatible motherboard socket and passive cooling infrastructure; it cannot be used in standard PCIe slots or workstations without that support.

Also in this aisle

People compared these

Same shelf, same checkout — eight coins and a 30-minute rate lock.