NVIDIA TITAN RTX
- Graphics Processor
- TU102
- Cores
- 4608
- TMUs
- 288
- ROPs
- 96
- Memory Size
- 24 GB
- Memory Type
- GDDR6
- Bus Width
- 384 bit
GPU
I/O
Top
Cooler
Back
Recommended Resolutions:
- 640x480
- 1280x720
- 1366x768
- 1600x900
- 1920x1080
- 2560x1440
- 3840x2160
The TITAN RTX is a enthusiast-class graphics card by NVIDIA, launched in December 2018. Built on the 12 nm process, and based on the TU102 graphics processor, in its TU102-400-A1 variant, the card supports DirectX 12.0. The TU102 graphics processor is a large chip with a die area of 754 mm² and 18,600 million transistors. It features 4608 shading units, 288 texture mapping units and 96 ROPs. Also included are 576 tensor cores which help improve the speed of machine learning applications. The card also has 72 raytracing acceleration cores. NVIDIA has placed 24,576 MB GDDR6 memory on the card, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 1350 MHz, which can be boosted up to 1770 MHz, memory is running at 1750 MHz.
Being a dual-slot card, the NVIDIA TITAN RTX draws power from 2x 8-pin power connectors, with power draw rated at 280 W maximum. Display outputs include: 1x HDMI, 3x DisplayPort, 1x USB Type-C. TITAN RTX is connected to the rest of the system using a PCI-Express 3.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 2499 US Dollars.
Being a dual-slot card, the NVIDIA TITAN RTX draws power from 2x 8-pin power connectors, with power draw rated at 280 W maximum. Display outputs include: 1x HDMI, 3x DisplayPort, 1x USB Type-C. TITAN RTX is connected to the rest of the system using a PCI-Express 3.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 2499 US Dollars.
Graphics Processor
- GPU Name
- TU102
- GPU Variant
- TU102-400-A1
- Architecture
- Turing
- Foundry
- TSMC
- Process Size
- 12 nm
- Transistors
- 18,600 million
- Die Size
- 754 mm²
Graphics Card
- Release Date
- Dec 18th, 2018
- Generation
- GeForce 20
- Predecessor
- GeForce 10
- Production
- Active
- Launch Price
- 2,499 USD
- Bus Interface
- PCIe 3.0 x16
- Reviews
- 6 in our database
Relative Performance
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.
Clock Speeds
- Base Clock
- 1350 MHz
- Boost Clock
- 1770 MHz
- Memory Clock
-
1750 MHz
14000 MHz effective
Memory
- Memory Size
- 24 GB
- Memory Type
- GDDR6
- Memory Bus
- 384 bit
- Bandwidth
- 672.0 GB/s
Render Config
- Shading Units
- 4608
- TMUs
- 288
- ROPs
- 96
- SM Count
- 72
- Tensor Cores
- 576
- RT Cores
- 72
- L1 Cache
- 64 KB (per SM)
- L2 Cache
- 6 MB
Theoretical Performance
- Pixel Rate
- 169.9 GPixel/s
- Texture Rate
- 509.8 GTexel/s
- FP16 (half) performance
- 32.62 TFLOPS (2:1)
- FP32 (float) performance
- 16.31 TFLOPS
- FP64 (double) performance
- 509.8 GFLOPS (1:32)
Board Design
- Slot Width
- Dual-slot
- Length
- 10.5 inches
267 mm
- TDP
- 280 W
- Suggested PSU
- 600 W
- Outputs
- 1x HDMI
3x DisplayPort
1x USB Type-C
- Power Connectors
- 2x 8-pin
- Board Number
- PG150 SKU 0
Graphics Features
- DirectX
- 12.0 (12_1)
- OpenGL
- 4.6
- OpenCL
- 2.0
- Vulkan
- 1.1.122
- CUDA
- 7.5
- Shader Model
- 6.4