GeForce RTX 2070

GeForce RTX 2070
  • Graphics Processor: TU106
  • Cores: 2304
  • TMUs / ROPs: 144 / 64

Review

Gaming
29
Workstation
37
AI/ML
28
Energy Efficiency
28
NanoReview Final Score
31
Compare GeForce RTX 2070 with other GPUs

Games

FPS Table
Forza Horizon 5
109
70
56
40
The Witcher 3
124
100
73
38
Counter-Strike 2
181
132
96
48
Far Cry 6
92
83
64
34
Hogwarts Legacy
65
56
41
19
CoD: Modern Warfare III
79
74
50
34
Ghost of Tsushima
64
50
36
20
Cyberpunk 2077
67
63
35
15
Shadow of the Tomb Raider
106
98
68
36
Average FPS by Resolution
1080p High 99
1080p Ultra 81
1440p Ultra 58
4K Ultra 32
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
8492
Time Spy 9074
Solar Bay 39675
Port Royal 5194
Fire Strike 23208
Wild Life Extreme 18257
Night Raid 92357
Sources: 3DMark [1]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
97923
Background Blur 200 img/sec
Face Detection 106.8 img/sec
Horizon Detection 3.73 Gpixels/sec
Edge Detection 4.57 Gpixels/sec
Gaussian Blur 4.84 Gpixels/sec
Feature Matching 1.07 Gpixels/sec
Stereo Matching 452 Gpixels/sec
Particle Physics 11141.9 FPS
API OpenCL
Sources: Geekbench [3]

Cinebench 2024 GPU

Hardware benchmark using Maxon's Cinema 4D rendering engine
Cinebench 2024 GPU
5899

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
16057
G2D Mark 816
DirectX 11 130 FPS
DirectX 12 61 FPS
GPU Compute 6376 Ops/s
Sources: PassMark [5]16971 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
2196.03
Sources: Blender [9]932 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
12633
GB6 ML Half Precision
20355
GB6 ML Quantized
8999
Image Classification (SP) 5244
Image Segmentation (HP) 9644
Image Super Resolution (Q) 13716
Face Detection (HP) 21326
Pose Estimation (Q) 57284
Text Classification (SP) 1857
Machine Translation (HP) 2542
Object Detection (SP) 6466
Depth Estimation (Q) 22978
Style Transfer (SP) 111896
Framework ONNX
Backend DirectML
Sources: Geekbench [9]

Specifications

Detailed technical specifications of the GeForce RTX 2070

General

Vendor Nvidia
Build Discrete
Released October 17, 2018
Launch price (MSRP) $599
Case Desktop
Purpose Gaming
Segment Mid-range
Architecture Turing
GPU Codename TU106
AMD Equivalent - Radeon RX 5700 XT
Successor - GeForce RTX 5070
Recommended CPU - Intel Core i7 9700K or above
Desktop GPU rating - 63rd place

Graphics Processing Unit

Base Clock 1410 MHz
Boost Clock 1620 MHz
Shading Units 2304
Texture Mapping Units (TMUs) 144
Render Output Units (ROPs) 64
Compute Units (Pipelines) 36
Tensor Cores 288
Ray-tracing Cores 36
L1 Cache 64KB per cluster
L2 Cache 4MB shared
Instructions Per Cycle 2 IPC

Raw Performance

Pixel Fill Rate 104 GPixel/s
Texture Fill Rate 233 GTexel/s
FLOPS (FP32)
7.5 TFLOPS

Physical

Interface PCIe 3.0 x16
TGP 175 W
Manufacturing TSMC
Fabrication Process 12 nm
Die Size 445 mm²
Transistor Count 10 billion
Transistor Density 22.47 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? Please, use comment form below
🌐 Register your profile and become part of NanoReview community!