Accelerate AI model inference for applications like conversational AI and natural language processing (NLP). The A30 is suitable for small to medium-scale deep learning training, fine-tuning, and transfer learning, offering a practical option for budget-conscious projects.
Support your scientific and engineering simulations such as energy modeling and computational fluid dynamics (CFD). The A30 provides dependable performance for traditional HPC tasks, making it a viable choice for established workflows.
Efficiently process and analyze large datasets. The A30 performs well in GPU-accelerated ETL operations, real-time analytics, and machine learning tasks, offering a balanced approach to data processing.
Our Tesla A30 GPU is powered by the NVIDIA A30 accelerator, built on the Ampere architecture to deliver balanced performance for AI inference, training, data analytics, and HPC workloads. With 24 GB of HBM2 memory and support for Multi-Instance GPU (MIG), it enables efficient resource utilization across a wide range of use cases.
This GPU is optimized for real-world applications such as NLP, computer vision, ETL operations, and scientific computing. Ideal for teams seeking scalable AI performance with low power consumption and strong cost-efficiency.
GPU A30 enables data scientists and researchers to accelerate tasks like energy modeling, genomics, and computational fluid dynamics (CFD) simulations. Major frameworks such as TensorFlow and PyTorch run efficiently, making the NVIDIA A30 a versatile choice for production and research environments.
The A30 GPU is optimized for AI workloads like natural language processing, conversational AI, computer vision tasks, and recommendation systems. It delivers consistent performance for small to medium-scale training, fine-tuning, and transfer learning while maintaining efficient resource usage.
As a proven Ampere-generation GPU, the NVIDIA A30 offers effective acceleration for mainstream data analytics. It reliably speeds up ETL operations and data processing with frameworks like Apache Spark and RAPIDS, making it a pragmatic and cost-effective choice for data engineering and improving large-scale pipeline performance.
Our NVIDIA GPU A30 provides a solid balance between cost and performance. Choose between four different options, from 1 to 4 GPUs, coming with SSD storage from 100 GB up to 1.6 TB, depending on the chosen instance type.
| RAM | CPU Cores | GPU Cards | Min Local Storage | Max Local Storage | Price / Hour ({{ currency | uppercase }}) | |
|---|---|---|---|---|---|---|
| Small | 56 GB | 12 Cores | 1 GPU | 100 GB | 800 GB | {{ prices.opencompute.gpua30.small[currency] | number:8 }} |
| Medium | 90 GB | 16 Cores | 2 GPU | 100 GB | 1.2 TB | {{ prices.opencompute.gpua30.medium[currency] | number:8 }} |
| Large | 120 GB | 24 Cores | 3 GPU | 100 GB | 1.6 TB | {{ prices.opencompute.gpua30.large[currency] | number:8 }} |
| Huge | 225 GB | 48 Cores | 4 GPU | 100 GB | 1.6 TB | {{ prices.opencompute.gpua30.huge[currency] | number:8 }} |
Local Storage is not included in the displayed Instances price, and has a cost of {{ prices.opencompute.volume[currency] | number:8 }} {{ currency | uppercase }} / GiB hour.
Instance needs to be shutdown for hypervisor and platform updates as it cannot be live-migrated.
Available in the following Zones: CH-GVA-2
Please note that GPU instances require account validation: access is provided with priority to established businesses, and is granted after a manual screening process.
Combine the simplicity and scalability of the Exoscale Cloud with the power of NVIDIA A30. With our Docker-based template, you can access the full potential of the NVIDIA GPU Cloud (NGC) and significantly reduce time to solution.
NVIDIA GPU Cloud (NGC) provides a selected set of GPU-optimized software for artificial intelligence applications, visualizations, and HPC. The NGC Catalog includes containers, pre-trained models, Helm charts for Kubernetes deployments, and specific AI toolkits with SDKs.
NGC catalog works with both Exoscale Compute Instances and Exoscale Hosted & Managed Kubernetes. The image template for Kubernetes worker nodes embeds the optimized version of the container runtime for GPU A30 cards, making it quick work to start any application from the catalog without fiddling with drivers and CUDA versions.
24 GB high-bandwidth memory (HBM2) ensures rapid data transfers, enabling smooth execution of AI workloads, data analytics, and HPC applications.
Each A30 GPU card is provided with dedicated resources, ensuring consistent performance for your applications without resource contention.
Benefit from NVIDIA's Ampere architecture, offering strong compute capabilities and efficiency for its class.
The NVIDIA A30 is optimized for High-Performance Computing (HPC), AI inference, deep learning training, and data analytics, making it a versatile choice for many projects.
Partition your Tesla A30 GPU into up to 4 separate, isolated instances to efficiently manage multiple applications simultaneously, enhancing resource utilization.
As a sovereign European Cloud Provider, Exoscale ensures all your data is stored in the country of your chosen zone, fully GDPR compliant.
| Description | Specifications |
|---|---|
| Graphic Card | NVIDIA A30 |
| Cuda Cores per card | 10752 |
| Tensor Cores per card | 336 |
| GPU memory per card | 24 GB |
| GPU cards | 1-4 |
| CPU cores | 12-48 |
| RAM per instance | 56-225 |
| SSD local storage | max. 1.6 TB (SATA) |
| Zone | CH-GVA-2 |
| Works with | Compute SKS Docker NVIDIA |
When running demanding AI inference, data analytics, or HPC workloads in the cloud, performance and reliability matter. Our GPU A30 instances, powered by the NVIDIA A30, help teams across Europe scale efficiently and cost-effectively with Exoscale.
Contact usDiscover more GPU Instances for Cloud Computing to power diverse compute, graphics, and AI tasks. Fully integrated with the Exoscale ecosystem.
Our Tesla V100-based GPU is recommended for deep learning, neural networks, AI, and more.
Discover
Our NVIDIA A40-based GPU is the all-rounder for AR, VR, simulations, rendering, AI, and more.
Discover
Our A5000-based GPU is an entry-level all-rounder for AR, VR, simulations, rendering, AI, and more. GPU A5000 is 100% liquid-cooled and leverages a heat-reuse platform for sustainable accelerated computations.
Discover
Our 3080ti-based GPU is an all-rounder for deep learning model training, image processing, natural language processing, and more. GPU 3080ti is 100% liquid-cooled and leverages a heat-reuse platform for sustainable accelerated computations.
Discover
NVIDIA Blackwell B300 GPUs are coming soon to Exoscale! Prepare to supercharge your AI and HPC workloads with unparalleled performance, featuring floating point 4-bit precision and huge GPU memory, building on our commitment to deliver the most powerful cloud infrastructure.
Contact UsThe NVIDIA A30 is a powerful GPU built for AI inference, data analytics, and high-performance computing. With 24 GB of high-bandwidth memory and support for multi-instance GPU (MIG) workloads, it delivers an efficient balance of performance and flexibility—ideal for teams running diverse and demanding tasks in the cloud.
The GPU A30 and A40 are designed for different workloads. Our GPU A30 is optimized for compute tasks like AI and HPC, featuring 24 GB of high-bandwidth HBM2 memory and supporting Multi-Instance GPU (MIG). The A40 targets professional visualization and rendering with 48 GB of GDDR6 memory, but lacks the MIG feature that makes our A30 instances ideal for efficiently running diverse, parallel workloads.
