GeForce RTX 4070 Ti SUPER

GeForce RTX 4070 Ti SUPER

$1395
1080p GamingRay Tracing
70 Gaming
72 Workstation
59 AI/ML
46 Energy Efficiency
69 NanoReview Final Score
25717 Steel Nomad Lite Score

Technical Specifications

Performance

Architecture Ada Lovelace
GPU Codename AD103
Base Clock 2340 MHz
Boost Clock 2610 MHz
Shading Units 8448
Tensor Cores 264
Ray-tracing Cores 66
Compute Units (Pipelines) 66

Memory

Memory Type GDDR6X
Memory Size 16 GB
Memory Clock 1313 MHz
Effective Memory Speed 21000 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
285 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 24, 2024

Other Specifications

Forza Horizon 5 209144139105
The Witcher 3 22219413875
Counter-Strike 2 28821316382
Far Cry 6 16615513382
Hogwarts Legacy 1471189452
CoD: Modern Warfare III 19018614496
Ghost of Tsushima 1351119459
Cyberpunk 2077 17015010547
Shadow of the Tomb Raider 267253196102
1080p High 199
1080p Ultra 169
1440p Ultra 134
4K Ultra 78
Margin of Error Low
Time Spy 24222
Solar Bay 116372
Port Royal 15789
Fire Strike 56337
Wild Life Extreme 49898
Night Raid 176338
Background Blur 331.7 img/sec
Face Detection 211.6 img/sec
Horizon Detection 9.63 Gpixels/sec
Edge Detection 13.7 Gpixels/sec
Gaussian Blur 13.9 Gpixels/sec
Feature Matching 2.15 Gpixels/sec
Stereo Matching 1210 Gpixels/sec
Particle Physics 33566 FPS
API OpenGL
G2D Mark 1237
DirectX 11 278 FPS
DirectX 12 119 FPS
GPU Compute 18304 Ops/s
Aztec Ruins Normal Tier 1300.6 FPS
Car Chase 1119.6 FPS
Manhattan 3.1.1 (1440p) 943.4 FPS
T-Rex 4724.8 FPS
Tessellation 8597.7 FPS
ALU 2 8528.7 FPS
Driver Overhead 2 289.1 FPS
OS Windows
Image Classification (SP) 12970
Image Segmentation (HP) 26364
Image Super Resolution (Q) 37217
Face Detection (HP) 58720
Pose Estimation (Q) 177604
Text Classification (SP) 3815
Machine Translation (HP) 5829
Object Detection (SP) 15675
Depth Estimation (Q) 62447
Style Transfer (SP) 357918
Framework ONNX
Backend DirectML
Launch price (MSRP) $799
Case Desktop
Purpose Gaming
Segment High-end
Rival Equivalent Radeon RX 7900 XTX
Texture Mapping Units (TMUs) 264
Render Output Units (ROPs) 96
L1 Cache 128KB per cluster
L2 Cache 48MB shared
Instructions Per Cycle 2 IPC
Pixel Fill Rate 251 GPixel/s
Texture Fill Rate 689 GTexel/s
Transistor Density 118.73 MTr/mm²
ECC No