





Professional-grade graphics processing power designed for demanding workloads. The PNY NVIDIA RTX 4000 Ada features 20GB of dedicated GDDR6 memory, enabling seamless handling of large datasets, complex 3D rendering, and AI-accelerated applications. Built on Ada architecture for superior performance and efficiency. Ideal for content creators, engineers, and data scientists requiring reliable, enterprise-class GPU acceleration. Supports multiple display outputs and advanced compute capabilities for visualization and scientific computing tasks.
NVIDIA Tensor Cores 192
NVIDIA Ada Lovelace Architecture
GPU Memory 20 GB GDDR6 with ECC
CUDA Parallel Processing Cores 6,144.
| Product | NVIDIA RTX 4000 Ada Generation |
| Architecture | NVIDIA Ada Lovelace Architecture |
| Foundry | TSMC |
| Process Size | 4 nm NVIDIA Custom Process |
| Transistors | 35.8 billion |
| Die Size | 294.5 mm2 |
| CUDA Parallel Processing Cores | 6,144 |
| NVIDIA Tensor Cores | 192 |
| NVIDIA RT Cores | 48 |
| Single-Precision Performance1 | 26.7 TFLOPS |
| RT Core Performance1 | 61.8 TFLOPS |
| Tensor Performance1 | 327.6 TFLOPS2 |
| GPU Memory | 20 GB GDDR6 with ECC |
| Memory Interface | 160-bit |
| Memory Bandwidth | 360 GB/s |
| Max Power Consumption | 130W |
| Graphics Bus | PCI Express 4.0 x16 |
| Display Connectors | DP 1.4a (4)3 |
| Form Factor | 4.4″ (H) x 9.5″(L) Single Slot |
| Product Weight | 528 g |
| Thermal Solution | Blower Active Fan |
| NVIDIA 3D Vision® and 3D Vision Pro | Support via 3-pin mini DIN |
| Frame Lock | Compatible (with Quadro Sync II) |
| NVLink | Not Supported |
| NVENC | NVDEC | 2x | 2x (+AV1 Encode & Decode) |
Thanks for subscribing!
This email has been registered!