NVIDIA TITAN RTX
Benchmark and Specs

Last updated:

Description

Here we show you benchmarks and technical data for the NVIDIA TITAN RTX. The graphics card is based on the NVIDIA TITAN RTX (Turing) and has 24 GB GDDR6 of graphics memory with a bandwidth of 672 GB/s.

The total 4608 shader units of the NVIDIA TITAN RTX are clocked with a maximum of 1.77 GHz. The graphics card thus achieves an FP32 computing power of 16.31 TFLOPS and was released in Q4/2018.

GPU

The NVIDIA TITAN RTX has 4608 shaders and 72 execution units. The graphics card thus achieves a theoretical FP32 computing power of 16.31 TFLOPS.

Based on: NVIDIA TITAN RTX
GPU Chip: TU102-400-A1 (Turing)
Streaming Multiprocessors: 72
Shader: 4608
Render Output Units: 96
Texture Units: 288
Raytracing Cores: 72

Memory

The NVIDIA TITAN RTX can use 24 GB graphics memory of the type GDDR6. The graphics card thus achieves a memory bandwidth of 672 GB/s on a 384 bit wide memory interface.

Memory Size: 24 GB
Memory Type: GDDR6
Memory Clock: 1.750 GHz
Memory Speed: 14 Gbps
Memory bandwidth: 672 GB/s
Memory Interface: 384 bit

Clock Speeds

The base clock frequency of the NVIDIA TITAN RTX is 1.350 GHz. A high clock frequency (even in turbo mode) can greatly increase the speed of a graphics card.

Base Clock: 1.350 GHz
Boost Clock: 1.770 GHz
Avg (Game) Clock:
Overclocking: Yes

Thermal Design

The TDP (Thermal Design Power) of the NVIDIA TITAN RTX is 280 W. The graphics card is supplied with energy via the 2 x 8-Pin connector.

TDP: 280 W
TDP (up): --
Tjunction max: 89 °C
PCIe-Power: 2 x 8-Pin

Cooler & Fans

The NVIDIA TITAN RTX has a total of 2 Axial fans to cool the graphics processor and graphics memory.

Fan-Type: Axial
Fan 1: 2 x 90 mm
Fan 2: --
Cooler-Type: Air cooling
Noise (Idle): 0 dB / Silent
Noise (Load): --

Connectivity

Up to 4 screens can be connected to the NVIDIA TITAN RTX.

Max. Displays: 4
HDCP-Version: --
HDMI Ports: 1x HDMI v2.0b
DP Ports: 3x DP v1.4a
DVI Ports: --
VGA Ports: --
USB-C Ports: 1

Featureset

The NVIDIA TITAN RTX has a maximum resolution of 7680x4320 pixels. The graphics card supports the DirectX 12_2 standard.

Max. resolution: 7680x4320
DirectX: 12_2
Raytracing: Yes
DLSS / FSR: No
LED: No LED lighting

Supported Video Codecs

The video codecs accelerated in hardware by the NVIDIA TITAN RTX reduce the processor load and ensure lower energy consumption.

h264: Decode / Encode
h265 / HEVC: Decode / Encode
VP8: Decode / Encode
VP9: Decode / Encode
AV1: No

Dimensions

The NVIDIA TITAN RTX is 267 mm long and 116 mm high. With a width of 35 mm, the graphics card requires 2 PCIe-Slots in the case.

Length: 267 mm
Height: 116 mm
Width: 35 mm
Width (Slots): 2 PCIe-Slots
Weight: --

Additional data

The NVIDIA TITAN RTX made in 12 nm was published in Q4/2018 for 2,499 $ (Reference).

GPU Interface: PCIe 3.0 x 16
Release date: Q4/2018
Launch Price: 2,499 $ (Reference)
Structure size: 12 nm
Part-no: 900-1G150-2500-000
Documents: data sheet

Benchmark results

3DMark Benchmark (DirectX, Raytracing) - Time Spy Graphics score

3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value. Here at GPU-Monkey we only use selected benchmarks for the graphics card, which are determined with a sufficiently fast processor so that the processor does not negatively affect the performance of the graphics card.
View all 3DMark Benchmark (DirectX, Raytracing) benchmark results



3DMark Benchmark (DirectX, Raytracing) - Time Spy Extreme Graphics score

3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value. Here at GPU-Monkey we only use selected benchmarks for the graphics card, which are determined with a sufficiently fast processor so that the processor does not negatively affect the performance of the graphics card.
View all 3DMark Benchmark (DirectX, Raytracing) benchmark results



3DMark Benchmark (DirectX, Raytracing) - Fire Strike Extreme Graphics score

3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value. Here at GPU-Monkey we only use selected benchmarks for the graphics card, which are determined with a sufficiently fast processor so that the processor does not negatively affect the performance of the graphics card.
View all 3DMark Benchmark (DirectX, Raytracing) benchmark results



3DMark Benchmark (DirectX, Raytracing) - Port Royal (Raytracing)

3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value. Here at GPU-Monkey we only use selected benchmarks for the graphics card, which are determined with a sufficiently fast processor so that the processor does not negatively affect the performance of the graphics card.
View all 3DMark Benchmark (DirectX, Raytracing) benchmark results



3DMark Benchmark (DirectX, Raytracing) - Speed Way Graphics Score (Raytracing)

3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value. Here at GPU-Monkey we only use selected benchmarks for the graphics card, which are determined with a sufficiently fast processor so that the processor does not negatively affect the performance of the graphics card.
View all 3DMark Benchmark (DirectX, Raytracing) benchmark results



Geekbench 5 (CUDA, OpenCL, Vulkan, Metal) - Geekbench 5 - CUDA (NVIDIA only)

Geekbench 5 is primarily a cross-platform benchmark for main processors, which runs through various tests in order to finally output the processor's performance in the form of a numerical value. In addition to the CPU benchmark, Geekbench can also run 4 different graphics benchmarks and output them in the form of a numerical value.
Zusätzlich zum CPU-Benchmark kann Geekbench auch 4 verschiedene Grafik-Benchmarks durchführen und in Form eines Zahlenwertes ausgeben.
View all Geekbench 5 (CUDA, OpenCL, Vulkan, Metal) benchmark results



Geekbench 5 (CUDA, OpenCL, Vulkan, Metal) - Geekbench 5 - OpenCL

Geekbench 5 is primarily a cross-platform benchmark for main processors, which runs through various tests in order to finally output the processor's performance in the form of a numerical value. In addition to the CPU benchmark, Geekbench can also run 4 different graphics benchmarks and output them in the form of a numerical value.
Zusätzlich zum CPU-Benchmark kann Geekbench auch 4 verschiedene Grafik-Benchmarks durchführen und in Form eines Zahlenwertes ausgeben.
View all Geekbench 5 (CUDA, OpenCL, Vulkan, Metal) benchmark results



Geekbench 5 (CUDA, OpenCL, Vulkan, Metal) - Geekbench 5 - Vulkan

Geekbench 5 is primarily a cross-platform benchmark for main processors, which runs through various tests in order to finally output the processor's performance in the form of a numerical value. In addition to the CPU benchmark, Geekbench can also run 4 different graphics benchmarks and output them in the form of a numerical value.
Zusätzlich zum CPU-Benchmark kann Geekbench auch 4 verschiedene Grafik-Benchmarks durchführen und in Form eines Zahlenwertes ausgeben.
View all Geekbench 5 (CUDA, OpenCL, Vulkan, Metal) benchmark results



FP32 Performance (Single-precision TFLOPS) - FP32 (TFLOPS)

The theoretical computing power of the graphics card with single precision (32 bit) in TFLOPS. TFLOPS indicates how many trillion FP32 floating point operations the graphics card (GPU) can perform per second. The larger this number, the faster the graphics card is.

View all FP32 Performance (Single-precision TFLOPS) benchmark results



More benchmarks

In order to determine the performance of a graphics card, so-called "benchmarks" are carried out. The benchmark software carries out special calculations to determine the performance of a graphics card. We use so-called theoretical or synthetic benchmarks (e.g. 3D Mark) as well as real game benchmarks. To ensure real comparability of the results, we pay attention to the correct execution of the benchmarks as well as the condition of the graphics card and the system.

We use the following benchmarks to measure the performance of a graphics card:

Recommended power supplies for this graphics card

Power Supply PCIe 8 Pin (6+2) Launch Price
Seasonic PRIME FANLESS TX-700 Seasonic PRIME FANLESS TX-700 - 700 W 4 x 249 $
EVGA SuperNOVA 750 P2 EVGA SuperNOVA 750 P2 - 750 W 6 x 160 $
Corsair TX-M Series TX750M 2017 Corsair TX-M Series TX750M 2017 - 750 W 4 x 121 $
Corsair HX Series HX750 Corsair HX Series HX750 - 750 W 4 x 169 $
EVGA SuperNOVA 750 G3 EVGA SuperNOVA 750 G3 - 750 W 6 x 125 $
be quiet! Straight Power 11 be quiet! Straight Power 11 - 750 W 4 x 139 $
Corsair RMx Series RM750x White Corsair RMx Series RM750x White - 750 W 4 x 139 $
EVGA SuperNOVA 750 G5 EVGA SuperNOVA 750 G5 - 750 W 6 x 145 $
Seasonic PRIME TX-750 Seasonic PRIME TX-750 - 750 W 4 x 205 $
Seasonic PRIME PX-750 Seasonic PRIME PX-750 - 750 W 4 x 169 $



Popular comparisons

1. NVIDIA TITAN RTX Gainward GeForce RTX 4090 Phantom NVIDIA TITAN RTX vs Gainward GeForce RTX 4090 Phantom
2. NVIDIA TITAN RTX NVIDIA GeForce RTX 4080 Founders Edition NVIDIA TITAN RTX vs NVIDIA GeForce RTX 4080 Founders Edition
3. NVIDIA TITAN RTX NVIDIA GeForce RTX 3090 Ti Founders Edition NVIDIA TITAN RTX vs NVIDIA GeForce RTX 3090 Ti Founders Edition
4. NVIDIA TITAN RTX ASUS Dual GeForce RTX 3070 NVIDIA TITAN RTX vs ASUS Dual GeForce RTX 3070
5. NVIDIA TITAN RTX ASUS ROG Strix GeForce RTX 4090 OC Edition NVIDIA TITAN RTX vs ASUS ROG Strix GeForce RTX 4090 OC Edition
6. NVIDIA GeForce GTX 1070 NVIDIA TITAN RTX NVIDIA GeForce GTX 1070 vs NVIDIA TITAN RTX
7. NVIDIA TITAN RTX NVIDIA GeForce RTX 3070 Ti Founders Edition NVIDIA TITAN RTX vs NVIDIA GeForce RTX 3070 Ti Founders Edition
8. NVIDIA TITAN RTX NVIDIA GeForce RTX 4070 Ti NVIDIA TITAN RTX vs NVIDIA GeForce RTX 4070 Ti
9. NVIDIA TITAN X Pascal NVIDIA TITAN RTX NVIDIA TITAN X Pascal vs NVIDIA TITAN RTX
10. ASUS TUF Gaming GeForce RTX 4080 16GB OC Edition NVIDIA TITAN RTX ASUS TUF Gaming GeForce RTX 4080 16GB OC Edition vs NVIDIA TITAN RTX


back to index
Facebook
Twitter