NVIDIA Tesla V100 SXM2 16GB HBM2, NVLink, GPU-NVTV100-SXM2
BUS: PCI-E 3.0 16x Memory size: 16 GB Stream processors: 5120 Theoretical performance: TFLOP
All NVIDIA Ampere, NVIDIA Grace Hopper, and NVIDIA Ada Lovelace GPU architectures are subject to a non-cancellable, non-returnable (NCNR) period of 52 weeks. Additionally, the product is subject to sanctions for certain countries and the end customer must be documented.
We can supply these GPU cards directly and with an individual B2B price. Contact us with your inquiry today.
| Product code | 214.154909 |
|---|---|
| Part number | 900-2G503-0000-000 |
| EAN | 672042301690 |
| Supermicro Part No. | GPU-NVTV100-SXM2 |
| Manufacturer | NVIDIA |
| Availability | Not in stock |
| Warranty | 24 months |
| Weight | 1 kg |
| The price includes all legal fees | |
Detailed information
NVIDIA Tesla
NVIDIA's Tesla products are a line of compute graphics processors that is very similar to NVIDIA's Quadro line (they usually use the same chip). But they have an isolated display interface. They are also available in passively cooled form, which is particularly suitable for use in servers (rackmount).
CUDA technology
Users of professional applications can use graphic CUDA stream processors thanks to the CUDA architecture. Thanks to this, the gross performance of the graphics card can be used for specific calculations, which can speed up the work many times compared to using a classic processor, which is significantly limited by a lower number of cores.
Product Specifications
| Main Specifications | ||
| Device type | GPU computing processor | |
| Form Factor | SXM2 | |
| Graphics Engine | NVIDIA Tesla V100 | |
| Interface Type | NVIDIA NVLink | |
| Memory | ||
| Bandwidth | 900 GBps | |
| Size | 16 GB | |
| Technology | HBM2 | |
| Video Output | ||
| API Supported | CUDA, DirectCompute, OpenCL, OpenACC | |
| CUDA Cores | 5120 | |
