NVIDIA RTX 4000 Ada Generation
Performance for Endless Possibilities
The NVIDIA RTX 4000 Ada Generation is the most powerful single-slot GPU for professionals, providing massive breakthroughs in speed and power efficiency over the previous generation to tackle demanding creative, design, and engineering workflows from the desktop. Harnessing the latest-generation RT Cores, Tensor Cores, and CUDA® cores alongside 20GB of graphics memory, RTX 4000 empowers professionals to create intricate product engineering, visionary cityscapes, and immersive entertainment experiences. With its power-efficient, single-slot design, RTX 4000 seamlessly fits into various workstation chassis, offering limitless potential for professionals.
Performance Highlights
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) |