NVIDIA A100 Tensor Core graphics card
TRY 795,819.00TRY 923,150.00 (-14%)
- NVIDIA A100 80GB PCIe Tensor Core GPU
- NVIDIA Ampere Architecture
- CUDA Cores 6912
- 1935 GB/s GPU Memory Bandwidth for faster data processing
- Advanced Third-Generation Tensor Cores for accelerated AI workloads
- Next-Generation NVLink
- High-Bandwidth Memory (HBM2E)
- Free installation support
- 24/7 Tech Support
- 1-year warranty
Description
Are you looking for a graphics card solution that delivers unmatched performance in AI, DL, ML, and HPC workloads to power the most scalable data centers in the world? Harness the advantages of powerful NVIDIA A100 80GB graphics cards that substantially accelerate tasks up to 3 times for stable diffusion, scientific simulations, and deep learning workloads in the world’s most elastic data centers. A100 uses MIG for optimal GPU utilization and Third-gen Tensor cores to provide 312 TFLOPS of DL performance. An HBM2e VRAM of up to 80GB is the fastest in the world, with a bandwidth of up to 1.94 Tbps and an adaptive DRAM usage efficiency of 95%. Speed up time to solution for the largest data analytics, business intelligence, HPC, cloud computing, and virtualization workflows. Built upon NVIDIA Ampere architecture, A100 combines the new sparsity feature to double the throughputs. PCI Express Gen 4 doubles the bandwidth to 15.75 GB/sec for x16 connections. Feed the massive computational potential to your bare metal servers and order from us with flexible pricing options and a 0% interest on EMI conversions. Enjoy free delivery in Turkey.
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) |
Product Information
Additional information
Brand | NVIDIA |
---|---|
GPU Memory | 80GB |
GPU Memory Bandwidth | 1935 GB/S |
Max Thermal Design Power (TDP) | 300W |
Form Factor | PCIe Dual-slot air-cooled or single-slot liquid-cooled |
Reviews (0)
FAQ
No FAQ Found
Reviews
There are no reviews yet.