H100
80GB SXM5 or 94GB NVL per GPU
View GPU All GPUsA100
Ampere architecture80GB HBM2e per GPU
GPU Catalog / NVIDIA
A100
GPU infrastructure.
An Ampere data-center GPU for established deep-learning, scientific-computing, and analytics stacks.
- Architecture
- Ampere
- GPU memory
- 80GB HBM2e per GPU
- Published from
- $1.49 / hr
Published pricing
Available configurations.
Current Geodd hourly rates. GPU memory totals reflect the accelerator count in each published configuration.
| Configuration | Variant | Total GPU memory | Hourly rate | Action |
|---|---|---|---|---|
1x GPUgpu_1x_a100 | A100 SXM | 80GB HBM2e80GB HBM2e each | $1.49per hour | Deploy |
2x GPUgpu_2x_a100 | A100 SXM | 160GB HBM2e80GB HBM2e each | $2.98per hour | Deploy |
4x GPUgpu_4x_a100 | A100 SXM | 320GB HBM2e80GB HBM2e each | $5.96per hour | Deploy |
8x GPUgpu_8x_a100 | A100 SXM | 640GB HBM2e80GB HBM2e each | $11.92per hour | Deploy |
Hardware profile
Where A100 fits.
The listed A100 configuration is the 80GB SXM variant with HBM2e memory. NVIDIA positions A100 for deep-learning training and inference, double-precision scientific simulation, and GPU-accelerated data analytics.
Choose A100 when an established Ampere software path is preferred and the workload benefits from 80GB of HBM2e per GPU.
NVIDIA product information- 01
Deep learning
Train and serve neural networks on an Ampere platform widely used for data-center AI workloads.
- 02
Scientific simulation
Run double-precision simulations and other GPU-accelerated high-performance computing applications.
- 03
Data analytics
Accelerate data preparation, analysis, and model pipelines that keep substantial data on the GPU.
Deployment sizing
Size before you provision.
Hardware fit depends on the model, precision, batch size, software stack, and total working set. Published use cases are not performance guarantees.
- 01 / Memory
Confirm the working set
Include weights, caches, activations, batches, and framework overhead.
- 02 / Software
Validate the stack
Check CUDA, driver, framework, precision, and container requirements.
- 03 / Capacity
Confirm provisioning
Published pricing does not guarantee immediate capacity in every configuration.