- Home
- Datacenters
- NVIDIA MLPerf v4.0 Submission 2024
Existing Confirmed
NVIDIA MLPerf v4.0 Submission 2024
NVIDIA • June 12, 2024
Total GPUs
11.6K
H100 Equiv
11.6K
Power
16.6 MW
FP16
11.5K PF
System Equivalents
This datacenter's 11.6K GPUs equal:
NVIDIA DGX H100
8 GPUs/system
1.5K
NVIDIA HGX H100 (8-GPU)
8 GPUs/system
1.5K
NVIDIA HGX H100 (4-GPU)
4 GPUs/system
2.9K
Specifications
| Primary GPU | NVIDIA H100 SXM5 80GB |
| GPU Count | 11.6K |
| Sector | Private |
Additional Information
In this round of MLPerf Training, NVIDIA has more than tripled its submission scale to 11,616 H100 GPUs and more than tripled performance to 3.4 minutes to train,
It seems likely that this could be an expansion on the NVIDIA Eos-DFW supercomputer