GeForce RTX 4080 SUPER

GeForce RTX 4080 SUPER

$1800
AAA GamingVR ReadyRay Tracing
78 Gaming
76 Workstation
66 AI/ML
46 Energy Efficiency
75 NanoReview Final Score
30716 Steel Nomad Lite Score

Technical Specifications

Performance

Architecture Ada Lovelace
GPU Codename AD103
Base Clock 2295 MHz
Boost Clock 2550 MHz
Shading Units 10240
Tensor Cores 320
Ray-tracing Cores 80
Compute Units (Pipelines) 80

Memory

Memory Type GDDR6X
Memory Size 16 GB
Memory Clock 1438 MHz
Effective Memory Speed 23000 Mbps
Bus 256-bit

Graphics APIs

DirectX 12
Vulkan 1.3
OpenGL 4.6
OpenCL 3.0
CUDA 8.9
Ray Tracing Yes
DLSS DLSS 3
DisplayPort 1.4a

Technical

TGP
320 W
Fabrication Process 5 nm
Die Size 379 mm²
Transistor Count 45 billion
Interface PCIe 4.0 x16
Manufacturing TSMC
Vendor Nvidia
Build Discrete
Released January 31, 2024

Other Specifications

Forza Horizon 5 231168154126
The Witcher 3 24321615680
Counter-Strike 2 31021916785
Far Cry 6 18216214392
Hogwarts Legacy 16213611060
CoD: Modern Warfare III 219212169114
Ghost of Tsushima 15012511171
Cyberpunk 2077 19417912458
Shadow of the Tomb Raider 283263201107
1080p High 219
1080p Ultra 187
1440p Ultra 148
4K Ultra 88
Margin of Error Low
Time Spy 28287
Solar Bay 138739
Port Royal 18344
Fire Strike 63709
Wild Life Extreme 60063
Night Raid 180001
Background Blur 279.5 img/sec
Face Detection 220.1 img/sec
Horizon Detection 11 Gpixels/sec
Edge Detection 15.2 Gpixels/sec
Gaussian Blur 16.2 Gpixels/sec
Feature Matching 2.08 Gpixels/sec
Stereo Matching 1370 Gpixels/sec
Particle Physics 37199.7 FPS
API OpenGL
G2D Mark 1274
DirectX 11 301 FPS
DirectX 12 134 FPS
GPU Compute 19741 Ops/s
Aztec Ruins Normal Tier 1384.7 FPS
Car Chase 1210.8 FPS
Manhattan 3.1.1 (1440p) 1001.1 FPS
T-Rex 5172 FPS
Tessellation 9573.9 FPS
ALU 2 9885.2 FPS
Driver Overhead 2 284.9 FPS
OS Windows
Image Classification (SP) 12453
Image Segmentation (HP) 34467
Image Super Resolution (Q) 43534
Face Detection (HP) 70300
Pose Estimation (Q) 242331
Text Classification (SP) 3767
Machine Translation (HP) 6614
Object Detection (SP) 18301
Depth Estimation (Q) 66477
Style Transfer (SP) 417906
Framework ONNX
Backend DirectML
Launch price (MSRP) $999
Case Desktop
Purpose Gaming
Segment High-end
Rival Equivalent Radeon RX 7900 XTX
Texture Mapping Units (TMUs) 320
Render Output Units (ROPs) 112
L1 Cache 128KB per cluster
L2 Cache 64MB shared
Instructions Per Cycle 2 IPC
Pixel Fill Rate 286 GPixel/s
Texture Fill Rate 816 GTexel/s
Transistor Density 118.73 MTr/mm²
ECC No