Skip to main content


The NVIDIA® Tesla® K40 companion processor is built for GPU computing. It features up to 2880 application-acceleration cores per board and 12 GB of memory, is the Tesla K40 GPU ideal for the most demanding HPC and big data problem sets. By adding a Tesla companion processor, engineers, designers, and content creation professionals can add over one Teraflop of computing potential to their workstation.

Features & Benefits

Features Benefits
  • K40 = 2880 Cores
  • Tesla K40 delivers up to 4.29 teraflops of single-percision floating point performance / 1.43 double-precision floating point performance
  • ECC Memory
  • Meets a critical requirement for computing accuracy and reliability in datacenters and supercomputing centers. Offers protection of data in memory to enhance data integrity and reliability for applications.
  • up to 12 GB of GDDR5 MEMORY per GPU
  • Maximizes performance and reduces data transfers by keeping larger data sets in local memory that is attached directly to the GPU.
  • Tesla GPUBoost
  • End-user can convert power headroom to higher clocks and achieve even greater acceleration for various HPC workloads on Tesla K40.

Technical details

Card categoryCoprocessor
Max. number per system unit2x in PRIMERGY RX350 S8
2x in PRIMERGY TX300 S8
Graphics memory speed3.0 GHz
Graphics memory bandwidth288 GB/sec
Power consumption235 W