GPUs

NVIDIA GeForce RTX 4080 Super Full Specs

10,240 Shaders
2.55GHz
16GB GDDR6X716.8GB/s
··
52.22 TFLOPS
Form Factor
PCIe Card
TDP
320W
Power Connectors
1x 16-Pin 12VHPWR

Clock Speed
···
Peak OPS
1.67 POPSINT4 Tensor Sparse
Tensor FP8-16
417.8 TFLOPS
FP8-16 Tensor Sparse
835.6 TFLOPS
Tensor FP8-32
208.9 TFLOPS
FP8-32 Tensor Sparse
417.8 TFLOPS
Tensor FP16-16
208.9 TFLOPS
FP16-16 Tensor Sparse
417.8 TFLOPS
Tensor FP16-32
104.4 TFLOPS
FP16-32 Tensor Sparse
208.9 TFLOPS
BF16
52.22 TFLOPS
Tensor BF16
104.4 TFLOPS
BF16 Tensor Sparse
208.9 TFLOPS
Tensor TF32
52.22 TFLOPS
FP32
52.22 TFLOPS
FP64
816 GFLOPS
Tensor INT4
835.6 TOPS
Tensor INT8
417.8 TOPS
Ray
120.7 TOPS
Pixel Rate
285.6 GPixel/s
Texture Rate
816 GTexel/s

Shaders
10,240 Shaders
TMUs
320 TMUs
ROPs
112 ROPs
Tensor Cores
320 T-Cores
RT Cores
80 RT-Cores
SMs
80 SMs

Base Clock
2.29GHz
Boost Clock
2.55GHz

L2 Cache
65.5MB shared

16GB GDDR6X
Memory Bus
256-bit
Memory Speed
22.4GT/s
Memory Bandwidth
716.8GB/s

TDP
320W
Max Temp
90°C Max

Multi-Monitor
4
HDCP
HDCP 2.3

3x DisplayPort 1.4
1x HDMI 2.1

Encoder Model
2x NVENC 8

Decoder Model
NVDEC 5

Form Factor
PCIe Card
PCIe
3-Slots
Height
137 mm (5.39")
Width
304 mm (11.97")
Depth
61 mm (2.4")
Cooling
Open-Air
2x Fans
Power Connectors
1x 16-Pin 12VHPWR

Manufacturer
Chip Designer
Architecture
Family
Branding
GeForce RTX 2022 branding
Codename
NV183
Chip Variant
AD103-275-A1
Market Segment
Desktop
Release Date
Jan 8, 2024

Foundry
TSMC
Fabrication Node
4N
Die Size
379mm²
Transistor Count
45.9 Billion
Transistor Density
121.2 MTr/mm²

No images available