- Model:VCNRTXA400ATX-PB
- 4GB GDDR6 memory
- 768 CUDA cores, NVIDIA Ampere architecture
- 4x Mini DisplayPort 1.4a, PCIe 4.0 x8
- 50W, single slot, 2.7" H x 6.4" L
- 3 Years Warranty from PNY
Overview
The NVIDIA RTX A400, built on the NVIDIA Ampere GPU architecture, brings the power of AI and ray-tracing acceleration into the hands of more professionals. The RTX A400 ensures AI-powered workflows and stunning ray-traced visuals are delivered with unprecedented performance in a space-saving design. With its compact form factor, the RTX A400 fits effortlessly into any workstation, providing the necessary performance and capabilities for today's professional workflows without compromising on efficiency or workspace.
Featuring 768 CUDA Cores, 24 third-generation Tensor Cores, and six second-generation RT Cores, the card delivers up to 2.7 TFLOPS single precision performance and 5.3 TFLOPS RT Core performance. The 4GB of GDDR6 memory with 96 GB/sec bandwidth boosts application performance, especially for content creation and CAD workflows, and compute-intensive tasks.
The RTX A400 supports up to four native 5K displays at 60Hz per card and includes dedicated H.264 and HEVC encode/decode engines for faster than real-time transcoding and video editing. It is ideal for architecture, engineering, construction, manufacturing, product development, media and entertainment professionals who need responsive performance for 3D modeling, CAD, rendering, video editing, and design software.
- NVIDIA Ampere Architecture
- 768 CUDA Cores with 24 Tensor Cores and 6 RT Cores
- 4GB GDDR6 memory with 96 GB/sec bandwidth
- 4x Mini DisplayPort 1.4a connectors
- PCIe Gen 4 x8 interface
- Second-generation RT Cores with up to 4X rendering performance
- Third-generation Tensor Cores for AI workflows
- H.264 and HEVC encode/decode engines
- NVIDIA RTX IO support
- NVIDIA Mosaic technology for multi-display support
Specifications
- GPU memory
- 4GB GDDR6
- Memory interface
- 64-bit
- Memory bandwidth
- 96GB/s
- NVIDIA Ampere architecture-basedCUDA Cores
- 768
- NVIDIA third-generation Tensor Cores
- 24
- NVIDIA second-generation RT Cores
- 6
- Single-precision performance
- 2.7 TFLOPs²
- RT Core performance
- 5.4 TFLOPs²
- FP16 Tensor performance
- 21.7 TFLOPs³
- Peak INT8 Tensor performance
- 43.3 TOPs⁴
- System Interface
- PCIe 4.0 x8⁵
- Power consumption
- Total board power: 50W
- Thermal solution
- Active
- Form factor
- 2.7”Hx6.4”L, single slot
- Display connectors
- 4x Mini DisplayPort 1.4a
- Encode/decode engines
- 1x encode,1x decode(+AV1decode)
- Compute APIs
- CUDA11.6, OpenCL3.0, DirectCompute
Warranty
3 Years manufacturer warranty from PNY. Warranty service is provided by the brand's authorised service centre under the brand's own terms; keep the original invoice and the serial number for any claim, and we will guide you through the process. Details are in our Warranty Policy.