NVIDIA A100 80GB Graphics Card
AED 84,500.00 AED 94,500.00 (-11%)
- Memory: 80GB HBM2e for high-performance computing
- Architecture: Advanced Ampere architecture
- Performance: Boosted by powerful Tensor Cores (640)for AI and ML workloads
- Interface: PCIe Gen4 for fast data transfer
- Power: 400W (SXM4) / 250W (PCIe)
- Applications: Ideal for AI, Deep Learning, Machine Learning, and HPC workloads
- Support: Free installation and 1-year warranty included
- Delivery: Fast and secure shipping
Are you looking to improve throughputs, produce high-quality graphics, or enhance the energy efficiency for your scalable and leading-edge data center? NVIDIA A100 80GB graphic cards are a perfect choice, as they offer an unmatched boost to data centers of any scale, energizing your HPC, deep learning, data analytics, and AI workloads. NVIDIA A100 is a powerful data center solution featuring a massive GPU memory and the fastest memory bandwidth of 2 TB/s, accelerating the response times, even in the expansive data sets and largest of the campuses. It is a dual-slot, PCIe Gen 4 graphics card, centered on NVIDIA Ampere architecture. It leverages 3rd Gen Tensor cores for the highest throughputs in math precision & compute-intensive tasks. The Multi-Instance GPU with the capacity to partition into multiple instances, each with its own high memory bandwidth and computing processors, provides the ability to adjust to changing workloads. Get the powerful data center platform delivered to your doorstep anywhere in the UAE swiftly at no additional cost. Own it with easy EMI options at 0% interest. Talk to us for pre-sales support.
Technical Specifications
Brand | NVIDIA |
---|---|
Product Name | NVIDIA A100 Tensor Core |
GPU architecture | NVIDIA Ampere |
GPU memory | 80GB |
CUDA Cores | 6912 |
Streaming Multiprocessors | 108 |
Tensor Cores | Gen 3 | 432 |
FP64 | 9.7 TFLOPS |
FP64 Tensor Core | 19.5 TFLOPS |
FP32 | 19.5 TFLOPS |
GPU Memory | 80GB HBM2e |
GPU Memory Bandwidth | 1,935 GB/s |
Max Thermal Design Power (TDP) | 300W |
NVLink | 2-Way, 2-Slot, 600 GB/s Bidirectional |
Multi-Instance GPU | Up to 7 MIGs @ 10GB |
Form Factor | PCIe Dual-slot air-cooled or single-slot liquid-cooled |
Graphics bus | PCIe 4.0 x16 |
Thermal solution | Passive |
vGPU Support | NVIDIA Virtual Compute Server (vCS) |
Additional information
Brand | NVIDIA |
---|---|
CUDA Cores | 6912 |
Tensor Cores | 432 |
GPU Memory | 80 GB HBM2E |
Memory Bandwidth | Up to 1.94 TB/s |
Max Thermal Design Power (TDP) | 300W |
GPU architecture | NVIDIA Ampere |
No FAQ Found
Reviews
There are no reviews yet.