GeForce RTX 2070 SUPER

GeForce RTX 2070 SUPER
  • Graphics Processor: TU104
  • Cores: 2560
  • TMUs / ROPs: 160 / 64

Review

Gaming
32
Workstation
39
AI/ML
33
Energy Efficiency
27
NanoReview Final Score
34
Compare GeForce RTX 2070 SUPER with other GPUs

Games

FPS Table
Forza Horizon 5
123
74
65
44
The Witcher 3
136
113
79
43
Counter-Strike 2
202
146
107
56
Far Cry 6
103
91
73
40
Hogwarts Legacy
74
61
46
25
CoD: Modern Warfare III
93
86
59
41
Ghost of Tsushima
73
58
41
26
Cyberpunk 2077
82
72
43
22
Shadow of the Tomb Raider
121
114
80
41
Average FPS by Resolution
1080p High 112
1080p Ultra 91
1440p Ultra 66
4K Ultra 38
Margin of Error Low

Test in Benchmarks

Performance tests in graphics benchmarks and applications

3D Mark

Multiplatform graphics benchmark suite that directly correlates with performance in modern games
Steel Nomad Lite Score
10047
Time Spy 10166
Solar Bay 45863
Port Royal 6032
Fire Strike 25679
Wild Life Extreme 20744
Night Raid 102662
Sources: 3DMark [1]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
105349
Background Blur 166.7 img/sec
Face Detection 103.3 img/sec
Horizon Detection 4.21 Gpixels/sec
Edge Detection 5.56 Gpixels/sec
Gaussian Blur 5.58 Gpixels/sec
Feature Matching 1.17 Gpixels/sec
Stereo Matching 489.7 Gpixels/sec
Particle Physics 13242.9 FPS
API OpenCL
Sources: Geekbench [3]

Cinebench 2024 GPU

Hardware benchmark using Maxon's Cinema 4D rendering engine
Cinebench 2024 GPU
6642

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
18123
G2D Mark 878
DirectX 11 154 FPS
DirectX 12 67 FPS
GPU Compute 7441 Ops/s
Sources: PassMark [5] – 20407 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
2352.17
Sources: Blender [9] – 1422 samples

Artificial Intelligence Tests

Performance in machine learning and artificial intelligence tasks

GeekBench 6 ML

Tests throughput of AI operations in single, half, and quantized precision
GB6 ML Single Precision
16276
GB6 ML Half Precision
27406
GB6 ML Quantized
10983
Image Classification (SP) 6648
Image Segmentation (HP) 16442
Image Super Resolution (Q) 15383
Face Detection (HP) 32861
Pose Estimation (Q) 66348
Text Classification (SP) 2166
Machine Translation (HP) 4239
Object Detection (SP) 8194
Depth Estimation (Q) 26192
Style Transfer (SP) 137642
Framework ONNX
Backend DirectML
Sources: Geekbench [9]

Specifications

Detailed technical specifications of the GeForce RTX 2070 SUPER

General

Vendor Nvidia
Build Discrete
Released July 9, 2019
Launch price (MSRP) $499
Case Desktop
Purpose Gaming
Segment Mid-range
Architecture Turing
GPU Codename TU104
Recommended CPU - Intel Core i7 9700K or above
Desktop GPU rating - 57th place

Graphics Processing Unit

Base Clock 1605 MHz
Boost Clock 1770 MHz
Shading Units 2560
Texture Mapping Units (TMUs) 160
Render Output Units (ROPs) 64
Compute Units (Pipelines) 40
Tensor Cores 320
Ray-tracing Cores 40
L1 Cache 64KB per cluster
L2 Cache 4MB shared
Instructions Per Cycle 2 IPC

Raw Performance

Pixel Fill Rate 113 GPixel/s
Texture Fill Rate 283 GTexel/s
FLOPS (FP32)
9.1 TFLOPS

Physical

Interface PCIe 3.0 x16
TGP 215 W
Manufacturing TSMC
Fabrication Process 12 nm
Die Size 545 mm²
Transistor Count 13 billion
Transistor Density 23.85 MTr/mm²

Memory

Memory Type GDDR6
Memory Size 8 GB
Memory Clock 1750 MHz
Effective Memory Speed 14000 Mbps
Bus 256-bit
ECC No
Memory Bandwidth
448 GB/s

API

DirectX 12
Vulkan 1.3
OpenGL 4.6
OpenCL 3.0
CUDA 7.5
Ray Tracing Yes
DLSS DLSS 2
DisplayPort 1.4a

Comments

Do you have any questions about RTX 2070 SUPER? Please, use comment form below
🌐 Register your profile and become part of NanoReview community!