NVIDIA® H200
From $3.59 /h*
Experience the best available GPU for Machine Learning
At the forefront of digital intelligence
Our servers exclusively use the NVIDIA H200 SXM5 141GB NVLINK modules.
Via NVLINK, the H200 achieves a chip-to-chip interconnect bandwidth of 900GB/s and leverages a 3200gbit/s InfiniBand™ interconnect.
Why SXM5?
Unmatched performance and speed-
Interconnect bandwidth
Significantly higher interconnect bandwidth, up to 3200 gbit/s RDMA interconnects -
Memory bandwidth
SXM5 features faster HBM3 memory with 3 TB/s compared to PCIe’s HBM2e 2 TB/s -
Power efficiency
Higher power consumption (700W) compared to PCIe (350W), enabling more intensive computational tasks -
Optimized for ML
SXM5 is ideal for large-scale HPC workloads and AI model training on massive datasets
H200 virtual dedicated servers are powered by:
Up to 8 NVIDIA H100 80GB GPUs, each containing 16896 CUDA cores and 528 Tensor Cores.
We only deploy the H100 on the H100 SXM5 platform, which offers a memory bandwidth of 3.35TB/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 name 8H100.80S.176V is composed as follows: 8x H100 SMX5, 176 CPU core threads & virtualized.
The 8xH100 VM has the same number of vCPUs as the 4xH100, 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.352V | H200 SXM5 141GB | 8 | 352 | 1480 | 1128 | 900 GB/s | $28.72/h | $27.57/h | $21.54/h |
| 4H200.141S.176V | H200 SXM5 141GB | 4 | 176 | 740 | 564 | 900 GB/s | $14.36/h | $13.79/h | $10.77/h |
| 2H200.141S.88V | H200 SXM5 141GB | 2 | 80 | 370 | 282 | 900 GB/s | $7.18/h | $6.89/h | $5.38/h |
| 1H200.141S.44V | H200 SXM5 141GB | 1 | 32 | 185 | 141 | / | $3.59/h | $3.45/h | $2.69/h |
DataCrunch Cloud
Where speed meets simplicity in GPU solutionsGPU clusters tailored to your needs
-
16x H200 Cluster
2x 8H200 bare metal systems
192C/384T AMD Genoa per node
512GB RAM
7.68TB local NVMe
800gbit InfiniBand
100gbit ethernet
Uplink 5gbit/s
Storage
Up to 300 TBTier 112 GB/sUp to 2 PBTier 23 GB/sUp to 10 PBTier 31 GB/s -
32x H200 Cluster
4x 8H200 bare metal systems
192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
1600gbit InfiniBand
100gbit ethernet
Uplink 5gbit/s
Storage
Up to 300 TBTier 112 GB/sUp to 2 PBTier 23 GB/sUp to 10 PBTier 31 GB/s -
64x H200 Cluster
8x 8H200 bare metal systems
192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
3200gbit InfiniBand
100gbit ethernet
Uplink 10gbit/s
Storage
Up to 300 TBTier 112 GB/sUp to 2 PBTier 23 GB/sUp to 10 PBTier 31 GB/s -
128x H200 Cluster
16x 8H200 bare metal systems
192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
3200gbit InfiniBand
100gbit ethernet
Uplink 25gbit/s
Storage
Up to 300 TBTier 112 GB/sUp to 2 PBTier 23 GB/sUp to 10 PBTier 31 GB/s