NVIDIA · Hopper · H100
80 GB of HBM3 at 2.0 TB/s, built for training, inference.
From $2.49/hracross 10 providers
Memory
80 GB
HBM3
Bandwidth
2.00 TB/s
FP16 tensor
1513 TFLOPS
FP8 tensor
3026 TFLOPS
Interconnect
PCIe
TDP
350 W
CUDA cores
14,592
Tensor cores
456
| Provider | Type | Spot | Details |
|---|---|---|---|
 RunPod | neocloud | Yes | View |
 Vast.ai | marketplace | Yes | View |
 CoreWeave | neocloud | — | View |
 Lambda | neocloud | — | View |
 Nebius | neocloud | — | View |
 Crusoe | neocloud | — | View |
 Amazon AWS | hyperscaler | Yes | View |
 Google Cloud | hyperscaler | Yes | View |
 Microsoft Azure | hyperscaler | Yes | View |
 Oracle Cloud | hyperscaler | Yes | View |
