What are the hardware requirements for installing DeepVA on-premises?
DeepVA runs on a modular system where performance can be scaled by adding more worker nodes—ideal for real-time or parallel processing—while a minimal setup is sufficient for slower, sequential analysis with lower resource usage.
DeepVA can be installed on-premises to meet specific privacy, security, or infrastructure requirements. The system is modular and scalable, allowing you to adjust hardware usage depending on your needs.
If you're looking for real-time or near-live processing, or you plan to run multiple AI modules simultaneously, you will need to deploy multiple worker nodes.
However, if processing speed and parallelization are not a priority, a single worker can analyze one module at a time. This slower but more cost-efficient setup is suitable for batch jobs or low-urgency tasks like metadata annotation for archives.
Contact us:
If you have questions or need guidance selecting the best setup for your workflow, our team is happy to assist—just reach out to us anytime!
Base System Requirements
These specifications cover the core platform services (API, databases, frontend):
-
CPU: 4 Cores
-
Memory (RAM): 16 GB
-
Storage: 512 GB SSD
Worker Node Requirements
Worker nodes handle the compute-heavy analysis tasks. The number of workers can be scaled based on your speed and concurrency requirements.
-
CPU: 4 Cores
-
Memory (RAM): 16 GB
-
Storage: 256 GB SSD
-
GPU:
-
Strongly recommended for performance
-
Minimum: NVIDIA GPU with 12 GB VRAM
-
Note:
Higher Speed / Real-Time Use Cases:
→ Deploy multiple workers and GPU acceleration
Cost-Efficient / Sequential Use Cases:
→ Use fewer workers with no GPU, processing one job at a time
Further Information: