Key Architecture Highlights
- FP32 Compute performance: 4.5 TF
- Tensor Compute performance: TF32 Tensor Core: Normal:9 TF; sparse:18 TF BFLOAT16 Tensor Core: Normal:18 TF; sparse:36 TF Peak FP16 Tensor Core: Normal:18 TF; sparse:36 TF
- Integer Compute performance: Peak INT8 Tensor Core: common:36 TOPS; sparse :72 TOPS Peak INT4 Tensor Core: common: 72 TOPS; sparse :144 TOPS
Applications
- AI training and inference
- High-performance computing
- Data center
Engineering Parameters
| FP32 Compute performance | 4.5 TF |
|---|---|
| Tensor Compute performance | TF32 Tensor Core: Normal:9 TF; sparse:18 TF BFLOAT16 Tensor Core: Normal:18 TF; sparse:36 TF Peak FP16 Tensor Core: Normal:18 TF; sparse:36 TF |
| Integer Compute performance | Peak INT8 Tensor Core: common:36 TOPS; sparse :72 TOPS Peak INT4 Tensor Core: common: 72 TOPS; sparse :144 TOPS |
| RT Cores | 10 |
| Video decoding | 1 video encoder 2 video decoders (includes AV1 decode) |
| GPU memory ／ Memory | 16GB GDDR6 |
| GPU memory bandwidth | 200GB/s |
| Interconnect Interface | PCIe Gen4 x8 |
| Form factor and installation | 1-slot, low-profile PCIe |
| Power consumption | 40–60W (configurable) |
Warranty
Public manufacturer information does not specify the warranty term applicable to our supply channel. The supply region, channel and actual warranty service are confirmed in the supply contract.
Manufacturer information
Manufacturer informationVerified Documentation & Datasheets
Manufacturer product information
Download Document