IBM NVIDIA 90Y2314 Tesla M2075 PCIe GPU Graphics Card

IBM Part #/MPN: 90Y2314

DiscTech Item #: IBM-90Y2314-NP-OE

  • Low Stock:Call for ETA
    Stock Levels

    This item is currently (nearly) out of stock. It may be possible to arrange fast shipment. If you need it urgently call us. Otherwise, it usually ships within 1 week.


Interface Types: PCIe

IBM NVIDIA 90Y2314 Tesla M2075 6GB GDDR5 PCIe Dual Slot GPU Companion Processor Graphics Card - New Pull

IBM NVIDIA 90Y2314 Tesla M2075 6GB GDDR5 PCIe / PCI Express Dual Slot GPU / Graphics Processing Unit Companion Processor Graphics Card

TESLA™ M-Class GPU Computing Modules

Based on the CUDA Architecture CodeNamed “FERMI,” the Tesla M-Class GPU Computing Modules are the world's fastest parallel computing processors for high performance computing (HPC). Tesla GPU's high performance makes them ideal for seismic processing, biochemistry simulations, weather and climate modeling, signal processing, computational finace, CAE, CFDAND Data Analytics.

Accelerate your Science with NVIDIA Tesla 20-series GPU's. A companion processor to the CPU in the server, Tesla GPU's speed up HPC applications by 10x. Based on the FERMI Architecture, these GPU's feature up to 665 Gigaflops of double precison performance, ECC Memory Error Protection and L1 adn L2 caches.

The Tesla M-Class GPU Modules are integrated into GPU-CPU servers from OEMs. This gives Data Center IT staff much greater choice in how they depoy GPUS, with a wide variety of rackmount and blade systems and with remote monitoring and management capabilities - enabling large Data Center, scal-out depoyments


  • Hundreds of CUDA Cores
  • Ecc Memory Error Protection
  • 6GB of GDDR5 Memory per GPU
  • System Monitoring Features
  • L1 and L2 Caches as part of the NVIDIA Parallel DataCache
  • NVIDIA Gigathread Engine
  • Asynchronous Transfer with Dual DMA Engines
  • Flexible Programming Environment with Board Support of Programming Languages and APIS

NVIDIA Tesla M2075 6GB GDDR5 2.0 X16 Graphics processor card AOC-GPU-NVM2075. The NVIDIA Tesla M2075 Graphics Processing Unit (GPU) Computing Module is a PCI Express, double-wide, full-height (4.376 inches by 9.75 inches by 1.52 inches) form factor computing module based on the NVIDIA FERMI GPU. This module comprises a computing subsystem with a GPU and high speed memory. The Tesla M2075 Module offers 6 GB of GDDR5 on-board memory.

The NVIDIA Tesla M2075 card have the following specifications:

  • NVIDIA Fermi GPU engine
  • 448 processor cores operating at 1.15 GHz
  • 6 GB GDDR5 (graphics DDR) memory operating at 1.566 GHz
  • PCIe x16 host interface
  • 225W (TDP) power consumption
  • Double Precision floating point performance (peak): 515 Gflops
  • Single Precision floating point performance (peak): 1.03 Tflops

Alt Model#: 900-21030-0472-100, 699-21030-0215-200, 900-21030-0070-100

Tesla M2000-series have no graphics output and are designed for GPGPU applications only.

NVIDIA Tesla M2075
Model Number90Y2314
Alt Model Number900-21030-0472-100
Graphics Processor
GPU NameGF110
GPU VariantGF110-876-A1
ArchitectureFermi 2.0
Process Size40 nm
Transistors3,000 million
Die Size520 mm
Bus InterfacePCIe 2.0x16
Memory Size6144 MB
Memory TypeGDDR5
Memory Bus384 bit)
Bandwidth150.3 GB/s
Clock Speeds
GPU Clock574 MHz
Shader Clock1147 MHz
Memory Clock783 MHx
3132 MHz effective
Graphics Features
DirectX12.0 (11_0)
Shader Model5.1
Render Config
Shading Units448
SM Count14
Pixel Rate16.07 GPixel/s
Texture Rate32.14 GTexel/s
Floating-point performance1,028 GFLOPS
Board Design
Slot WidthDual-slot
Length9*.75 inches
248 mm
TDP225 W
OutputsNo Outputs
Power Connectors(1) 6-pin
(1) 8-pin

Click here to view the manufacturer's item description/brochure

Alternate MPNs: 900-21030-0472-100 699-21030-0215-200 900-21030-0070-100

Weight: 3 lb

Warranty: 1 Year DiscTech

New Pull

Condition Levels Explained

The product has been mounted in a brand new system (e.g. server), then removed from the system, before entering service. These products may have some hours of usage due to system build time / burn-in / testing etc. New Pulls are guaranteed to have at least 95% (often 99%) of their service life remaining , they may show signs of being physically mounted and dismounted. All handling is performed by trained technicians, taking full ESD precautions.

1 Year DiscTech Warranty

Product Warranties Explained

The product has a DiscTech warranty for the time period specified. View our limited warranty