NVIDIA Titan RTX Graphics Card

BH #NVTITANRTX24 • MFR #900-1G150-2500-000
NVIDIA Titan RTX Graphics Card
Key Features
  • 1350 MHz Core - Boostable to 1770 MHz
  • 4608 CUDA Cores
  • Turing Architecture
  • 24GB of GDDR6 VRAM
The NVIDIA Titan RTX Graphics Card is based on the Turing architecture and is designed to handle real-time 8K video editing. It has 576 tensor cores, which can provide up to 130 tensor TFLOPs of performance.
No Longer Available

True Know-How

Ask Our Experts



  • 1Description
  • 2Real-Time Ray Tracing & Deep Learning
  • 3USB Type-C with VirtualLink
  • 4SLI Ready
  • 5NVIDIA GPU Boost 4.0
  • 6NVIDIA Ansel
  • 7CUDA
  • 8NVIDIA NVLink
  • 9G-SYNC Ready

The NVIDIA Titan RTX Graphics Card is based on the Turing architecture and is designed to handle real-time 8K video editing. It has 576 tensor cores, which can provide up to 130 tensor TFLOPs of performance.

The front panel of the card features a variety of outputs. There are three DisplayPort outputs, one HDMI output, and one USB Type-C port with the VirtualLink standard. Computationally intensive programs can utilize the GPU's 4608 cores to accelerate tasks using CUDA or other APIs. It also has 24GB of GDDR6 VRAM.

For cooling, NVIDIA implemented a dual-fan cooler. The dual 13-blade fans produce three times the airflow and provides quiet acoustics. The full-card vapor chamber is two times larger to maximize heat spreading and heat transfer to the finstack. A forged and machine-finished diecast aluminum cover with diamond-cut edge detailing provides a rigid, lightweight frame for an open design with smooth, continuous curves.

Real-Time Ray Tracing & Deep Learning

The NVIDIA TITAN RTX platform enables real-time ray tracing of objects and environments with physically accurate shadows, reflections, refractions, and global illumination. The TITAN RTX features 11 GigaRays per second of real-time ray-tracing performance. It also has 576 multi-precision Turing Tensor Cores, providing up to 130 teraflops of deep learning performance.

USB Type-C with VirtualLink

VirtualLink is an open industry standard that enables next-gen VR headsets to connect with PCs and other devices using a single, high-bandwidth USB Type-C connector. The Alternate Mode of USB Type-C simplifies and speeds up VR setup time, avoiding key obstacles to VR adoption. VirtualLink connects with VR headsets to simultaneously deliver four high-speed HBR3 DisplayPort lanes, which are scalable for future uses, a USB 3.1 Gen 2 data channel for supporting high-resolution cameras and sensors, and provides up to 27 watts of power.

SLI Ready

With a compatible motherboard and a connecting bracket, two or more NVIDIA GPUs of the same model can combine processing power using NVIDIA's Scalable Link Interface (SLI). How the cards work together can be customized to suit your preferences. Alternate frame rendering has each alternating card prepare the next frame, essentially multiplying the capabilities of a single card's maximum capable frame rate output. Each card in the configuration can also be used to improve anti-aliasing by being able to process an image in parallel with the other cards before filtering out jagged edges.

The NVIDIA GeForce RTX NVLink Bridge (sold separately) provides 50 times the available transfer bandwidth of previous technologies. Delivering smooth gameplay, it's an effective way to enjoy surround gaming and it's only compatible with the GeForce RTX 2080 and 2080 Ti graphics cards.

Note: The benefits of SLI will vary based on component configuration.

NVIDIA GPU Boost 4.0

Boosts the card's clock speed in real-time based on the target temperature. If the card is running below the set target temperature, GPU Boost 4.0 will increase the clock speed to improve performance. The target temperature can be reset depending on your preference so you can have the card run more quietly for everyday tasks and older games, and run at full tilt during intense high-resolution gaming sequences.


With Ansel, gamers can compose the gameplay shots they want, pointing the camera in any direction and from any vantage point within a gaming world. They can capture screenshots at up to 32 times the screen resolution, and then zoom in where they choose without losing fidelity. With photo-filters, they can add effects in real-time before taking the shot. And they can capture 360-degree stereo photospheres for viewing in a VR headset or Google Cardboard.


NVIDIA's parallel computing platform which enables an increase in computing performance by harnessing the parallel nature of GPU processing. CUDA-compatible applications can assign intensive parallel computing tasks, such as real-time video rendering, to the GPU to process, freeing up the computer's CPU to run other tasks.


With 100 GB/s NVLink, you can pair two TITAN RTX GPUs to scale memory and compute.

G-SYNC Ready

When used with a monitor that has G-SYNC hardware installed, the monitor's refresh rate will sync and lock with the graphics card's output frame rate. Establishing this sync removes tearing and stuttering which can result from conventional fixed screen refresh rates, especially important for gaming in stereoscopic 3D. An additional benefit of G-SYNC is reduced lag so gamers will benefit from the improved command response time as well.


Stream Processors72
4608 CUDA Cores
Boost Clock Speed1770 MHz
Base Clock Speed1350 MHz
Floating Point Performance130.00 TFLOPS
Memory Speed14 Gb/s
Memory Configuration24 GB
Memory InterfaceGDDR6
Memory Interface Width384-Bit
Memory Bandwidth672 GB/s
Display Support
Display Connectors3 x DisplayPort
1 x HDMI
1 x USB Type-C
Power Requirements
Max Power Consumption280 W
PCI Power Connectors2 x 8-Pin
Recommended System Power Requirement650 W
Cooler TypeOpen Fansink
Packaging Info
Package Weight4.585 lb
Box Dimensions (LxWxH)13 x 6.9 x 3.6"


See any errors on this page? Let us know