H200 virtual dedicated servers are powered by:
Up to 8 NVIDIA® H200 141GB GPUs, each containing 16896 CUDA cores and 528 Tensor Cores.
This is the current flagship silicon from NVidia®, unbeaten in raw performance for AI operations.
We only deploy the H200 in the SXM5 form-factor, which offers a memory bandwidth of 4.8TB/s and up to 900GB/s P2P bandwidth.
The servers utilize the fourth generation AMD Genoa, 384 threads with a boost clock of 3.7GHz, offering a substantial uplift in performance vs. alternatives.
The 8H200 VM has the same number of vCPUs as the 4H200, but delivers higher CPU performance by utilizing only the physical cores, rather than the logical processors (hyper-threads).
Instance name | GPU model | GPU | CPU | RAM | VRAM | P2P | On demand price | 6-month price | 2-year price |
---|---|---|---|---|---|---|---|---|---|
8H200.141S.176V | H200 SXM5 141GB | 8 | 176 | 1450 | 1128 | 900 GB/s | $24.24/h | $23.27/h | $18.18/h |
4H200.141S.176V | H200 SXM5 141GB | 4 | 176 | 740 | 564 | 900 GB/s | $12.12/h | $11.64/h | $9.09/h |
2H200.141S.88V | H200 SXM5 141GB | 2 | 88 | 370 | 282 | 900 GB/s | $6.06/h | $5.82/h | $4.54/h |
1H200.141S.44V | H200 SXM5 141GB | 1 | 44 | 185 | 141 | / | $3.03/h | $2.91/h | $2.27/h |
H100 virtual dedicated servers are powered by:
Up to 8 NVIDIA® H100 80GB GPUs, each containing 16896 CUDA cores and 528 Tensor Cores.
'This is the current flagship silicon from NVIDIA, unbeaten in raw performance for AI operations.
We deploy the SXM5 NVLINK module, which offers a memory bandwidth of 2.6 Gbps and up to 900GB/s P2P bandwidth.
Fourth generation AMD Genoa, up to 384 threads with a boost clock of 3.7GHz.
The name 8H100.80S.176V is composed as follows: 8x H100 SMX5, 176 CPU core threads & virtualized.
The 8H100 VM has the same number of vCPUs as the 4H100, but delivers higher CPU performance by utilizing only the physical cores, rather than the logical processors (hyper-threads).
Instance name | GPU model | GPU | CPU | RAM | VRAM | P2P | On demand price | 6-month price | 2-year price |
---|---|---|---|---|---|---|---|---|---|
8H100.80S.176V | H100 SXM5 80GB | 8 | 176 | 1480 | 640 | 900 GB/s | $21.20/h | $20.35/h | $15.90/h |
4H100.80S.176V | H100 SXM5 80GB | 4 | 176 | 740 | 320 | 900 GB/s | $10.60/h | $10.18/h | $7.95/h |
2H100.80S.80V | H100 SXM5 80GB | 2 | 80 | 370 | 160 | 900 GB/s | $5.30/h | $5.09/h | $3.97/h |
1H100.80S.32V | H100 SXM5 80GB | 1 | 32 | 185 | 80 | / | $2.65/h | $2.54/h | $1.99/h |
1H100.80S.30V | H100 SXM5 80GB | 1 | 30 | 120 | 80 | / | $2.65/h | $2.54/h | $1.99/h |
A100 virtual dedicated servers are powered by:
Up to 8 NVIDIA® A100 80GB GPUs, each containing 6912 CUDA cores and 432 Tensor Cores.
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 name 8A100.176V is composed as follows: 8x RTX A100, 176 CPU core threads & virtualized.
Instance name | GPU model | GPU | CPU | RAM | VRAM | P2P | On demand price | 6-month price | 2-year price |
---|---|---|---|---|---|---|---|---|---|
8A100.176V | A100 SXM4 80GB | 8 | 176 | 960 | 640 | 600 GB/s | $13.20/h | $12.67/h | $9.90/h |
4A100.88V | A100 SXM4 80GB | 4 | 88 | 480 | 320 | 300 GB/s | $6.60/h | $6.34/h | $4.95/h |
2A100.44V | A100 SXM4 80GB | 2 | 44 | 240 | 160 | 100 GB/s | $3.30/h | $3.17/h | $2.47/h |
1A100.22V | A100 SXM4 80GB | 1 | 22 | 120 | 80 | / | $1.65/h | $1.58/h | $1.24/h |
8A100.40S.176V | A100 SXM4 40GB | 8 | 176 | 960 | 320 | / | $10.32/h | $9.91/h | $7.74/h |
4A100.40S.88V | A100 SXM4 40GB | 4 | 88 | 480 | 160 | / | $5.16/h | $4.95/h | $3.87/h |
2A100.40S.44V | A100 SXM4 40GB | 2 | 44 | 240 | 80 | / | $2.58/h | $2.48/h | $1.94/h |
1A100.40S.22V | A100 SXM4 40GB | 1 | 22 | 120 | 40 | / | $1.29/h | $1.24/h | $0.97/h |
L40S virtual dedicated servers are powered by:
Up to 8 NVIDIA® L40S 48GB GPUs, each containing 18176 CUDA cores and 568 Tensor Cores.
Features 864GB/s memory bandwidth.
Tensor Performance: 1466 Tflops
RT Core Performance: 212 Tflops
Single-precision performance: 91.6 Tflops
The name 8L40S.160V is composed as follows: 8x L40S, 160 CPU core threads & virtualized.
Instance name | GPU model | GPU | CPU | RAM | VRAM | P2P | On demand price | 6-month price | 2-year price |
---|---|---|---|---|---|---|---|---|---|
8L40S.160V | NVIDIA L40S | 8 | 160 | 480 | 384 | 50GB/s | $8.80/h | $8.45/h | $6.60/h |
4L40S.80V | NVIDIA L40S | 4 | 80 | 240 | 192 | 50GB/s | $4.40/h | $4.22/h | $3.30/h |
2L40S.40V | NVIDIA L40S | 2 | 40 | 120 | 96 | 50GB/s | $2.20/h | $2.11/h | $1.65/h |
1L40S.20V | NVIDIA L40S | 1 | 20 | 60 | 48 | / | $1.10/h | $1.06/h | $0.83/h |
RTX6000 ADA virtual dedicated servers are powered by:
Up to 8 NVIDIA® RTX6000 ADA [2022] GPUs, each containing 18176 CUDA cores, 568 fourth-generation Tensor Cores and 142RT cores.
Features 48GB of GDDR6 memory for working with the largest 3D models, render images, simulation and AI datasets.
The name 8RTX6000ADA.80V is composed as follows: 8x RTX6000ADA, 80 CPU core threads & virtualized.
Instance name | GPU model | GPU | CPU | RAM | VRAM | P2P | On demand price | 6-month price | 2-year price |
---|---|---|---|---|---|---|---|---|---|
8RTX6000ADA.80V | NVIDIA RTX6000 Ada 48GB | 8 | 80 | 480 | 384 | 50GB/s | $9.52/h | $9.14/h | $7.14/h |
4RTX6000ADA.40V | NVIDIA RTX6000 Ada 48GB | 4 | 40 | 240 | 192 | 50GB/s | $4.76/h | $4.57/h | $3.57/h |
2RTX6000ADA.20V | NVIDIA RTX6000 Ada 48GB | 2 | 20 | 120 | 96 | 50GB/s | $2.38/h | $2.28/h | $1.78/h |
1RTX6000ADA.10V | NVIDIA RTX6000 Ada 48GB | 1 | 10 | 60 | 48 | / | $1.19/h | $1.14/h | $0.89/h |
RTX A6000 virtual dedicated servers are powered by:
Up to 8 NVIDIA® RTX A6000 [2021] GPUs, each containing 10752 CUDA cores, 336 Tensor Cores and 84RT cores.
Despite having less tensor cores than the V100, it is able to process tensor operations faster due to a different architecture.
Second generation AMD EPYC Rome, up to 96 threads with a boost clock of 3.35GHz.
PCIe Gen4 for faster interactions between GPUs.
The name 8A6000.80V is composed as follows: 8x RTX A6000, 80 CPU core threads & virtualized.
Instance name | GPU model | GPU | CPU | RAM | VRAM | P2P | On demand price | 6-month price | 2-year price |
---|---|---|---|---|---|---|---|---|---|
8A6000.80V | NVIDIA RTX A6000 48GB | 8 | 80 | 480 | 384 | 50GB/s | $8.06/h | $7.74/h | $6.04/h |
4A6000.40V | NVIDIA RTX A6000 48GB | 4 | 40 | 240 | 192 | 50GB/s | $4.03/h | $3.87/h | $3.02/h |
2A6000.20V | NVIDIA RTX A6000 48GB | 2 | 20 | 120 | 96 | 50GB/s | $2.01/h | $1.93/h | $1.51/h |
1A6000.10V | NVIDIA RTX A6000 48GB | 1 | 10 | 60 | 48 | / | $1.01/h | $0.97/h | $0.76/h |
V100 virtual dedicated servers are powered by:
Up to 8 NVIDIA® Tesla V100 GPUs, each containing 5120 CUDA cores and 640 Tensor Cores.
Second generation Xeon Scalable 4214R CPUs [2020], up to 48 threads with a boost clock of 3.5GHz.
NVLink for high bandwidth P2P communication.
The name 4V100.20V is composed as follows: 4x V100, 20 CPU core threads & virtualized.
Instance name | GPU model | GPU | CPU | RAM | VRAM | P2P | On demand price | 6-month price | 2-year price |
---|---|---|---|---|---|---|---|---|---|
8V100.48V | NVIDIA Tesla V100 16GB | 8 | 48 | 180 | 128 | NVLink up to 50GB/s | $3.12/h | $3.00/h | $2.34/h |
4V100.20V | NVIDIA Tesla V100 16GB | 4 | 20 | 90 | 64 | NVLink up to 50GB/s | $1.56/h | $1.50/h | $1.17/h |
2V100.10V | NVIDIA Tesla V100 16GB | 2 | 10 | 45 | 32 | NVLink up to 50GB/s | $0.78/h | $0.75/h | $0.58/h |
1V100.6V | NVIDIA Tesla V100 16GB | 1 | 6 | 23 | 16 | / | $0.39/h | $0.37/h | $0.29/h |
CPU virtual dedicated servers are powered by:
Second or Third generation AMD EPYC Rome or Milan.
All hardware is dedicated to your server for the best performance.
The name CPU.32V indicates the server runs on 32 virtualized core threads.
Instance name | CPU model | CPU | RAM | P2P | On demand price | 6-month price | 2-year price |
---|---|---|---|---|---|---|---|
CPU.360V.1440G | AMD EPYC | 360 | 1440 | / | $3.60/h | $3.46/h | $2.70/h |
CPU.180V.720G | AMD EPYC | 180 | 720 | / | $1.80/h | $1.73/h | $1.35/h |
CPU.120V.480G | AMD EPYC | 120 | 480 | / | $1.20/h | $1.15/h | $0.90/h |
CPU.96V.384G | AMD EPYC | 96 | 384 | / | $0.96/h | $0.92/h | $0.72/h |
CPU.64V.256G | AMD EPYC | 64 | 256 | / | $0.64/h | $0.61/h | $0.48/h |
CPU.32V.128G | AMD EPYC | 32 | 128 | / | $0.32/h | $0.31/h | $0.24/h |
CPU.16V.64G | AMD EPYC | 16 | 64 | / | $0.16/h | $0.15/h | $0.12/h |
CPU.8V.32G | AMD EPYC | 8 | 32 | / | $0.08/h | $0.08/h | $0.06/h |
CPU.4V.16G | AMD EPYC | 4 | 16 | / | $0.04/h | $0.04/h | $0.03/h |
Storage
Our instances run on a network storage cluster. This cluster allows us to constantly keep your data in 3 copies, to ensure redundancy in the event of hardware failure.
Our NVMe cluster offers high IOPS and excellent continuous bandwidth, the HDD cluster is ideal for larger datasets. By default, the volume sizes are limited, however, the limits can be increased on demand.
Type | Continuous Bandwidth [MB/s] | Burst Bandwidth [MB/s] | IOPS | Internal Network Speed [GBit/s] | Price [$/GB/Month] |
---|---|---|---|---|---|
NVMe | 2000 | 2500 | 100k | 50 | 0.2 |
HDD | 250 | 2000 | 300 | 50 | 0.05 |
NVMe_Shared | N/A | N/A | N/A | N/A | 0.2 |