Key Architecture Highlights
- GPU Architecture: NVIDIA Hopper
- GPU memory specifications: GPU memory: 80 GB GPU memory Type: HBM2e GPU memory ECC: Enabled
- GPU memory bandwidth: 2,000 GB/s
Applications
- AI training and inference
- High-performance computing
- Analysis of data
Engineering Parameters
| GPU Architecture | NVIDIA Hopper |
|---|---|
| GPU memory specifications | GPU memory: 80 GB GPU memory Type: HBM2e GPU memory ECC: Enabled |
| GPU memory bandwidth | 2,000 GB/s |
| GPU memory bus width | 5,120 bit |
| PCIe Interface | PCIe Gen5 x16/x8, also denoted as Gen4 x16. |
| NVLink / Interconnection | NVLink: Supports The next two. Card NVLink Bridge., Use 3 units NVLink Bridge. |
| MIG Division | Support for up to 7 instances |
| Board power | 350W default/maximum, minimum 200W ((16-pin 450W/600W power input mode); 310W default/maximum, minimum 200W ((16-pin 300W power input mode) |
| Power input Interface | 1 PCIe 16-pin power input interface |
| Card form factor / cooling | card form factor: Full length (FHFL) 10.5 ton, double-slit cooling method: passive cooling (requires server wind tunnel) |
| GPU Frequency | Base: 1,125 MHz Boost: 1,755 MHz |
Warranty
manufacturer's public product information does not specify the warranty period for this model in its supply channel; applicable region, channel and actual warranty service confirmed by the supply contract.
Manufacturer information
Manufacturer informationVerified Documentation & Datasheets
Official products page
Download DocumentPB-11133-001_v02 | November 2022 NVIDIA H100 PCIe GPU Product Brief
Download Document