NVIDIA H100 SXM
Hopper-architecture datacenter GPU for large-scale AI training
~$30000
Datacenter
80GB
HBM3
3350
GB/s bandwidth
67
FP32 TFLOPS
700W
TDP
16896
cores
4nm
process
// about NVIDIA H100 SXM
The H100 is Nvidia data center GPU built on the Hopper architecture, used to train and serve most large-scale AI models today.
// similar hardware in Datacenter
NVIDIA B200
NVIDIA Blackwell flagship datacenter GPU for frontier model training
NVIDIA · Datacenter · N/A
NVIDIA GB200 NVL72
Rack-scale Grace Blackwell superchip for trillion-parameter models
NVIDIA · Datacenter · N/A
NVIDIA GB300 NVL72
Rack-scale Blackwell Ultra superchip with expanded memory
NVIDIA · Datacenter · N/A
NVIDIA H100 PCIe
PCIe-form-factor Hopper datacenter GPU
NVIDIA · Datacenter · ~$25000
NVIDIA H200
High-memory Hopper refresh for large-model inference
NVIDIA · Datacenter · ~$32000
NVIDIA Rubin R100
Successor to Blackwell built for agentic-scale AI
NVIDIA · Datacenter · N/A