Key Architecture Highlights
- Cores Configuration: Turing Tensor Cores: 320; NVIDIA CUDA® cores: 2,560
- Calculator Compute performance: Single Precision Performance (FP32): 8.1 TFLOPS; Mixed Precision (FP16/FP32): 65 FP16 TFLOPS
- Integer Compute performance: INT8 Precision: 130 INT8 TOPS; INT4 Precision: 260 INT4 TOPS
Applications
- AI training and inference
- High-performance computing
- Data center
Engineering Parameters
| Cores Configuration | Turing Tensor Cores: 320 NVIDIA CUDA® cores: 2,560 |
|---|---|
| Calculator Compute performance | Single Precision Performance (FP32): 8.1 TFLOPS Mixed Precision (FP16/FP32): 65 FP16 TFLOPS |
| Integer Compute performance | INT8 Precision: 130 INT8 TOPS INT4 Precision: 260 INT4 TOPS |
| GPU memory ／ Memory | 16 GB GDDR6 |
| GPU memory bandwidth | 320+ GB/s |
| Power consumption / Form | 70W, compact PCIe form |
| Interconnect Interface | PCIe Gen3 x16 |
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