GPUSPECINDEX

NVIDIA · Turing (derived from codename prefix) · 2018

Titan RTX

Titan RTX: 24 GB GDDR6, 280 W, 4,608 CUDA cores. Launched December 18, 2018.

Memory
24 GB
Power
280 W
Bus width
384 bit
Memory24 GB2 of 5 in TITAN
Power280 W1 of 5 by higher draw in TITAN
CUDA cores4,6083 of 5 in TITAN

Affiliate links — we may earn a commission.

Memory

Capacity
24 GB
Memory type
GDDR6
Bus width
384 bit
Memory clock
1,750 MHz
Bandwidth
672 GB/s

Compute

CUDA cores
4,608
SM count
72
TMUs
288
ROPs
96
FP32
12,442 GFLOPS
FP64
389 GFLOPS
Pixel fill rate
129.6 GP/s
Texture fill rate
388.8 GT/s

Clocks

Boost clock
1,350 MHz

Board

TDP
280 W
External power required
Yes
Form factor
desktop

Physical

Architecture
Turing (derived from codename prefix)
Codename
TU102-400-A1
Transistors
18.6 billion
Die size
754 mm²
Series
TITAN
Launch date
December 18, 2018

Not recorded by the source: generation, process, base clock and bus interface, or 1 further field.

Silicon, made visible

Die area is drawn against the largest recorded die in the catalog. Shader dots use a labeled, card-specific ratio so both early and modern GPUs remain legible.

754 mm² die · 4,608 shadersDie area drawn to scale against the catalog maximum of 1,540 square millimeters. Each dot = 32 shaders.754 mm² die · 4,608 shadersEach dot = 32 shadersDashed frame = largest catalog die (1,540 mm²)

Within its series, the Titan RTX ranks first of 5 for FP32 throughput and second of 5 for memory capacity. Its 280 W TDP is above the 75 W PCIe slot-power ceiling.

Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16