NVIDIA HGX H100 640GB - 935-24287-0001-000
Graphics Engine: Hopper Memory size: 640 GB Number of tensor cores: 535 Theoretical performance: 268 TFLOP
All NVIDIA Ampere, NVIDIA Grace Hopper, NVIDIA Ada Lovelace GPU and NVIDIA Blackwell 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 | 214.166385 |
---|---|
Part number | 935-24287-0001-000 |
Supermicro Part No. | GPU-NVHGX-H100-LC-88-EX2 |
Manufacturer | NVIDIA |
Availability | ETA 4 weeks |
Warranty | 36 months |
Weight | 2 kg |
- Server system integrator & worldwide shipping
- Personal approach and tailor-made servers
- NBD warranties & cross-shipping
- Private cloud infrastructure
- Pre-sales & After-sales support
Detailed information
The listed price is indicative and for informational purposes only. The product cannot be purchased separately – it is available exclusively as part of a complete server configuration.
NVIDIA Server
NVIDIA's products present a range of professional graphics cards designed for both rackmount servers and powerful workstations. These are very high quality graphic products with large memory and a special set of drivers that are adapted to work in CAD and other professional applications as well as remote collaboration, virtual desktop, 3D visualization and rendering, but also for machine learning. Compared to desktop graphics cards, they are often also optimized for lower consumption.
268 TFLOPS
Hopper
Graphics memory
VRAM, these days primarily of GDDR type, is a synchronous memory, similar to standard RAM. However, in the case of graphic memory, memory chips with faster throughput and multiple data transfer rates are concerned. The result is a much faster buffering of data that the graphics card or coprocessor calculates and passes to the processor.
640
CUDA Technology
Users of professional applications can benefit from CUDA graphics stream processors thanks to CUDA architecture. Thanks to this, the raw power of the graphics card can be used for specific calculations, which can accelerate the work manifold compared to a classic processor, which is significantly limited by a lower amount of cores.
535
Passive
Passively cooled graphics cards do not have any powered moving components. They take advantage of optimized airflow, especially in a server environment, which takes heat away from the graphics unit outside of the case. Passive cooling is used especially for very powerful graphics coprocessors.
PCI Express
PCI Express is an interface that usually takes the form of an expansion slot to ensure the modularity of the entire system, whether it is GPU, network cards, controllers, M.2 drives or other expansion cards. It is true that the newer the generation and wider the interface, the higher the performance and throughput. Most modern graphics cards use 16 lanes to connect with the processor. Currently, the most up-to-date generation is PCI Express generation 4.0 with a speed of 2 Gb/s per lane.
Parameters
Product line | Tesla |
---|---|
Architecture | Hopper |
Gigabytes of memory | 640 |
Number of stream processors | 135168 |
Memory type | HBM2 |
Slot count | 0 |
Monitor output | None |
Profile | OCP |
Interface | HGX |
Cooling type | Passive |
Power consumption (W) | 5600 |