NVIDIA A10
GPU architecture NVIDIA Ampere
Universal accelerator computing and graphics (compute + graphics)
9216 NVIDIA CUDA cores for parallel computing
288 Tensor cores to accelerate AI and deep learning computing
24 GB of GPU memory for working with large models and datasets
Memory capacity up to 600 GB/s
Interface PCIe 4.0 x16 for high data throughput
Passive cooling suitable for servers and industrial systems
Maximum power consumption: 150 W
Free shipping from €300
Promocja cenowa na model HDR-15-5
Product intended for professional use only
NVIDIA A10
Description
NVIDIA A10 - a versatile GPU accelerator for data centres
NVIDIA A10 is a professional GPU based on the NVIDIA Ampere architecture, designed for modern data centres, AI environments and graphics virtualisation. The card combines high-performance computing with graphics rendering capabilities to support both advanced computing workloads and graphics applications.
A compact single-slot design with 150 W power consumption makes the NVIDIA A10 ideal for servers and industrial GPU systems where high compute density and energy efficiency are important. With support for NVIDIA virtual GPU (vGPU) technology, the card enables multiple virtual environments to run simultaneously while maintaining high graphics and computing performance.
Performance for AI, graphics and computing
The NVIDIA A10GPU offers 9216 CUDA cores and 288 Tensor cores to accelerate computing used in artificial intelligence systems, data analysis and scientific simulation. This makes the card ideal for environments using machine learning, deep learning and big data processing.
Additionally, 24 GB of GPU memory with up to 600 GB/s bandwidth allows the card to support demanding AI models, large graphics scenes and engineering applications. The PCIe 4.0 x16 interface provides high-bandwidth communication between the GPU and the server system.
GPU virtualisation and VDI infrastructure
One of the key benefits of the NVIDIA A10 is its full integration with the NVIDIA vGPU platform, which enables the computing power of a single GPU card to be shared among multiple users or virtual machines.
This makes the NVIDIA A10 an ideal solution for:
- virtualised workstations (VDI)
- remote CAD / 3D design environments
- rendering platforms
- AI and machine learning environments
- data centres running graphics applications
Ideal for scalable GPU systems
Passive cooling and optimised power consumption make the NVIDIA A10 primarily designed for installation in servers and high-density GPU computing systems. As a result, it can be part of scalable AI infrastructure and data processing platforms.
The card is used in GPU systems used in:
- video analysis and vision AI systems
- AI model training and inference
- digital twins and simulations
- graphics virtualisation
- 3D rendering
- data centre analysis
Technical Specification
| FP32 | 31.2 teraFLOPS |
|---|---|
| TF32 Tensor Core | 62.5 teraFLOPS | 125 teraFLOPS* |
| BFLOAT16 Tensor Core | 125 teraFLOPS | 250 teraFLOPS* |
| FP16 Tensor Core | 125 teraFLOPS | 250 teraFLOPS* |
| INT8 Tensor Core | 250 TOPS | 500 TOPS* |
| INT4 Tensor Core | 500 TOPS | 1,000 TOPS* |
| RT Core | 72 RT Cores |
| Encode/Decode | 1 encoder, 2 decoders (+ AV1 decode) |
| GPU Memory | 24 GB GDDR6 |
| GPU Memory Bandwidth | 600 GB/s |
| Interconnect | PCIe Gen4: 64 GB/s |
| Form Factor | Single-slot, full-height, full-length (FHFL) |
| Max Thermal Design Power (TDP) | 150 W |
| vGPU Software Support | NVIDIA Virtual PC, NVIDIA Virtual Applications, NVIDIA RTX Virtual Workstation, NVIDIA Virtual Compute Server, NVIDIA AI Enterprise |
*With Sparsity
