| INSTANCE NAME | GPU MODEL | GPU | CPU | RAM | VRAM | P2P | PRICE ON DEMAND | 6-MONTH PRICE | 2-YEAR PRICE |
|---|
The A100 virtual dedicated servers are powered by:
Up to 8 NVidia® A100 80GB GPUs, each containing 6912 CUDA cores and 432 Tensor Cores.
This is the current flagship silicon from NVidia®, unbeaten in raw performance for AI operations.
We only use the SXM4 'for NVLINK' module, which offers a memory bandwidth of over 2TB/s and Up to 600GB/s P2P bandwidth.
Second generation AMD EPYC Rome, up to 192 threads with a boost clock of 3.3GHz.
This is the current flagship silicon from NVidia®, unbeaten in raw performance for AI operations.
We only use the SXM4 'for NVLINK' module, which offers a memory bandwidth of over 2TB/s and Up to 600GB/s P2P bandwidth.
Second generation AMD EPYC Rome, up to 192 threads with a boost clock of 3.3GHz.
The GPU's are passed through to the dedicated virtual machines, which delivers native performance.
The servers are dedicated: the hardware is allocated to your machine and your machine only. Virtualization offers the best possible security for your data.
The name 8A100.176V is composed as follows; 8x RTX A100, 176 CPU core threads & virtualized.
Note: Once you deploy your instance, the price and discount are fixed and not subject to future changes.
The servers are dedicated: the hardware is allocated to your machine and your machine only. Virtualization offers the best possible security for your data.
The name 8A100.176V is composed as follows; 8x RTX A100, 176 CPU core threads & virtualized.
- The host servers run in a secured and ISO27001 certified datacenter facility and are owned and operated solely by DataCrunch.
- All DataCrunch operations are ISO27001 certified.
- The facility offers redundant power, your data is secured by storing it in 3 copies at all times.
Note: Once you deploy your instance, the price and discount are fixed and not subject to future changes.