GPUSPECINDEX

NVIDIA · Ampere (derived from codename prefix) · 2020

GeForce RTX 3080

GeForce RTX 3080: 10 GB GDDR6X, 320 W, 8,704 CUDA cores. Launched September 17, 2020 at $699.

Memory
10 GB
Power
320 W
Bus width
320 bit
Memory10 GB32 of 77 in GeForce RTX
Power320 W12 of 66 by higher draw in GeForce RTX
CUDA cores8,70416 of 78 in GeForce RTX
Launch price$69919 of 54 in GeForce RTX

Affiliate links — we may earn a commission.

Memory

Capacity
10 GB
Memory type
GDDR6X
Bus width
320 bit
Memory clock
1,188 MHz
Bandwidth
760.3 GB/s

Compute

CUDA cores
8,704
SM count
68
TMUs
272
ROPs
96
FP32
25,068 GFLOPS
FP64
392 GFLOPS
Pixel fill rate
138.24 GP/s
Texture fill rate
391.68 GT/s

Clocks

Boost clock
1,440 MHz

Board

TDP
320 W
Bus interface
PCIe 4 x16
Form factor
desktop
Launch MSRP
699 USD

Physical

Architecture
Ampere (derived from codename prefix)
Codename
GA102-200-KD-A1
Transistors
28.3 billion
Die size
628.4 mm²
Series
GeForce RTX
Launch date
September 17, 2020

Not recorded by the source: generation, process, base clock and external power required.

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.

628.4 mm² die · 8,704 shadersDie area drawn to scale against the catalog maximum of 1,540 square millimeters. Each dot = 64 shaders.628.4 mm² die · 8,704 shadersEach dot = 64 shadersDashed frame = largest catalog die (1,540 mm²)

Within its series, the GeForce RTX 3080 ranks 19th of 66 for FP32 throughput and 32nd of 77 for memory capacity. Its 320 W TDP is above the 75 W PCIe slot-power ceiling.

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