1 / 5
| Core parameters | Core architecture: Ampere (GAH100 GPU cores). Production process: 7nm. Number of transistors: 54 billion. CUDA cores: 6912. Core frequency: 1410MHz. |
| Video memory parameters | Video memory capacity: 94GB. Video memory type: HBM3e. Memory bit width: 5120 bits. Memory bandwidth: Approx. 2039GB/s. |
| Compute Performance | FP32 (Single Precision): ~19.5TFLOPS. FP64 (double): ~9.7TFLOPS. TF32: ~156TFLOPS. FP16/BF16: ~312TFLOPS (up to 624TFLOPS in sparse mode). INT8: ~624TOPS. |
| Interfaces & Interconnections | Interface type: PCI Express 4.0 x16 (PCIe 3.0 compatible). NVLink: supports NVLink Gen 3 (600GB/s bandwidth). Note: bridging is not supported in PCIe (only SXM4 version supports). |
| Power & Heat | Maximum power consumption: 300W. Heat dissipation: Server-grade passive heat dissipation, relying on chassis air ducts. |
| Advanced Features | Multi-Instance GPU (MIG): Single card can be divided into up to 7 independent instances. Supported technologies: CUDA 11, cuDNN, TensorRT, PyTorch, TensorFlow, and vGPUs. |
Silicon-based root of trust anchors end-to-end boot resilience while Multi-Factor Authentication (MFA) ensures trusted operations.
Simplify and centralize management with professional enterprise consoles and iDRAC for secure, efficient server solutions.
Energy-efficient options designed to reduce carbon footprint and lower operation costs through innovative engineering.
Typically equipped with four DisplayPort 1.4 ports and multi-screen outputs, professional users can connect multiple high-resolution displays: