Reserve your NVIDIA A100 GPU today with Civo
Be the first to add one of the most powerful NVIDIA GPUs into your infrastructure.
Find out more today
Unrivaled Scalability and Speed with NVIDIA A100 GPU
Find out more todayTake an in-depth look
| NVIDIA A100 GPU specifications | |
|---|---|
| GPU architecture | NVIDIA Ampere architecture |
| GPU memory | 40GB and 80GB HBM2e |
| Memory bandwidth | 2,039GB/s |
| NVIDIA Ampere Architecture-Based CUDA® cores | 6,912 |
| NVIDIA Third-Generation Tensor cores | 312 TFLOPS (TF32), 624 TFLOPS (FP16, BFLOAT16) |
| Single-precision performance (FP32) | 19.5 TFLOPS |
| Efficiency/Security features | NEBS Level 3, Secure Boot |
| Max power consumption | 400W (standard configuration) |
| Form factor | PCIe dual-slot air-cooled or single-slot liquid-cooled |
| Interconnect interface | NVIDIA NVLink Bridge for 2 GPUs: 600GB/s, PCIe Gen4: 64GB/s |
| Ideal for | AI/LLM Inference & Training, 3D Graphics |
Maximum GPU power at the lowest possible price
Industry-leading on-demand and standard pricing you won't find anywhere else.
| Model | Status | From price | On-demand price |
|---|---|---|---|
| A100 40GB | In stock now | $0.69 per GPU/h | $1.09 per GPU/h |
| A100 80GB | In stock now | $1.39 per GPU/h | $1.79 per GPU/h |
For full details on pricing and the savings you can make see our pricing page here.
Contact us and get a quote today
Unleash the full potential of AI with the NVIDIA A100 on Civo.
Contact us today to explore a solution that supports your most demanding AI workloads.