Get the best of accelerated computing with the NVIDIA H100 Tensor Core GPU, offering unprecedented performance, scalability, and security for every workload. With the NVIDIA NVLink Switch System, it can connect up to 256 H100 GPUs to accelerate exascale workloads. The dedicated Transformer Engine solves trillion-parameter language models, speeding up large language models by 30X over the previous generation. This delivers industry-leading conversational AI, making it a powerhouse for any application.

                  
                                          
                        
GPU Model
                        
NVIDIA H100 Tensor Core GPU
                      
                                          
                        
NVLink Switch System
                        
Up to 256 H100 GPUs
                      
                                          
                        
Transformer Engine
                        
Dedicated engine for trillion-parameter language models
                      
                                          
                        
Performance Boost
                        
30X over the previous generation
                      
                                          
                        
Application
                        
Accelerated computing, conversational AI
                      
                                          
                        
Weight
                        
3.5 lb
                      
                                          
                        
Length
                        
10.5 inch
                      
                                          
                        
Width
                        
4.5 inch
                      
                                          
                        
Height
                        
1.5 inch