{{ 'fb_in_app_browser_popup.desc' | translate }} {{ 'fb_in_app_browser_popup.copy_link' | translate }}
{{ 'in_app_browser_popup.desc' | translate }}
NVIDIA A800-80G is an advanced GPU designed for AI and HPC applications, offering scalable performance for data centers managing complex tasks. Ideal for engineers and procurement professionals seeking reliable solutions for high-performance computing and artificial intelligence projects.
Not enough stock.
Your item was not added to your cart.
Not enough stock.
Please adjust your quantity.
{{'products.quick_cart.out_of_number_hint'| translate}}
{{'product.preorder_limit.hint'| translate}}
Limit {{ product.max_order_quantity }} per order.
Only {{ quantityOfStock }} item(s) left.
NVIDIA A800-80G is an advanced GPU designed for AI and HPC applications, offering scalable performance for data centers managing complex tasks. Ideal for engineers and procurement professionals seeking reliable solutions for high-performance computing and artificial intelligence projects.
Features | Nvidia A800-80G | Nvidia A100-80G | Nvidia V100 | Nvidia T4 | AMD MI100 | AMD Instinct MI200 | Intel Nervana NNP-I |
---|---|---|---|---|---|---|---|
GPU Memory | 80 GB | 80 GB | 32 GB | 16 GB | 32 GB | 128 GB | 8 GB |
Performance (TFLOPS) | 312 TFLOPS | 312 TFLOPS | 130 TFLOPS | 65 TFLOPS | 181 TFLOPS | 383 TFLOPS | 19.5 TFLOPS |
Architecture | Ampere | Ampere | Volta | Turing | RDNA | CDNA | Spring Crest |
High Bandwidth Memory (HBM2) | Yes | Yes | No | No | Yes | Yes | No |
PCIe Support | PCIe 4.0 | PCIe 4.0 | PCIe 3.0 | PCIe 3.0 | PCIe 4.0 | PCIe 4.0 | PCIe 4.0 |
TDP | 400W | 400W | 250W | 70W | 300W | 450W | 75W |
Accessory | Model | Description |
---|---|---|
GPU Cooling System | Cooler Master MasterLiquid ML360 | High-performance liquid cooling system |
Power Supply Unit | Corsair AX1600i | 1600W digital power supply unit |
PCIe Riser Cable | Thermaltake TT Gaming PCIe 4.0 | Premium PCIe riser cable |
Nvidia A800-80G Specifications | |
GPU Architecture | Ampere |
CUDA Cores | 6912 |
Memory Type | HBM2e |
Memory Size | 80 GB |
Memory Bandwidth | 2 TB/s |
Tensor Cores | 432 |
FP32 Performance | 19.5 TFLOPS |
FP64 Performance | 9.7 TFLOPS |
Deep Learning Performance | 312 Tensor TFLOPS |
Interconnect Bandwidth | 600 GB/s |
Form Factor | PCIe |
NVLink | 2 Links |
ECC Memory | Yes |
Error Checking | Yes, ECC |
Board Power | 300 Watts |
Multi-GPU Support | Yes |
Server Compliance | Yes, validated for data centers |
Recommended PSU | 750 Watts |
Release Date | 2023 |
Manufacturer Warranty | 3 Years |