Home > GPU Comparison > RX 580 vs GTX 1660 Ti – what's better?

AMD Radeon RX 580 vs GeForce GTX 1660 Ti

Radeon RX 580
VS
GeForce GTX 1660 Ti
AMD Radeon RX 580
Polaris 20
Nvidia GeForce GTX 1660 Ti
TU116

We compared two discrete desktop gaming GPUs: the Radeon RX 580 8 GB with 2304 shaders against the 1 year and 10 months newer GeForce GTX 1660 Ti 6 GB that utilizes 24 pipelines and 1536 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.

  1. Review
  2. Differences
  3. Gaming performance
  4. Benchmarks
  5. AI
  6. Specs
  7. Comments

Review

General comparison of performance in games, applications, power efficiency, and other metrics
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score

Value for money (Beta)

We use average GPU prices from all manufacturers by default. Enter the current price of a specific card for better accuracy.
Currency
8 GB GDDR5
VS
6 GB GDDR6
48.2
(Average)
Value Index
25.7
(Mediocre)

Key differences

Key distinctions and advantages of GTX 1660 Ti over RX 580
Reasons to consider the Radeon RX 580
  • 15% higher maximum theoretical performance (6.2 vs 5.4 TFLOPS)
  • Includes 2 GB more video memory
  • Has 50% more shading units (2304 vs 1536)
Reasons to consider the GeForce GTX 1660 Ti
  • Performs significantly better (up to 42%) in 3DMark Steel Nomad Lite
  • Shows 52% higher average frame rate in modern games at QHD resolution – 41 vs 27 FPS
  • Manufactured using a more efficient 12 nm process technology
  • Achieves 79% more points in the GeekBench 6 Compute test (72K vs 40K)

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions
GPU
RX 580
vs
GTX 1660 Ti

Games

FPS Table
Forza Horizon 5
76
39
31
17
89
51
44
24
The Witcher 3
50
41
22
12
88
70
46
24
Counter-Strike 2
74
55
38
15
140
95
71
30
Far Cry 6
59
49
35
17
73
63
49
22
Hogwarts Legacy
34
26
20
9
49
40
26
15
CoD: Modern Warfare III
48
42
27
15
58
47
35
24
Ghost of Tsushima
33
23
19
10
45
35
24
14
Cyberpunk 2077
33
27
16
-
46
41
25
10
Shadow of the Tomb Raider
60
52
32
15
78
75
50
25
Average FPS by Resolution
1080p High 52 74
1080p Ultra 39 57
1440p Ultra 27 41
4K Ultra 13 21
Margin of Error Low Low

Benchmarks

Graphics cards’ performance in recent benchmarking apps

3D Mark

Multiplatform graphics benchmark suite that directly correlates with performance in modern games
Steel Nomad Lite Score
RX 580
4183
GTX 1660 Ti +42%
5943
Time Spy 4354 6339
Solar Bay - 20515
Port Royal 527 1649
Fire Strike 14980 16654
Wild Life Extreme 8907 13006
Night Raid 56859 76387
Sources: 3DMark [1], [2]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
RX 580
40514
GTX 1660 Ti +79%
72340
Background Blur 59.5 img/sec 124.8 img/sec
Face Detection 33.8 img/sec 69.4 img/sec
Horizon Detection 1.56 Gpixels/sec 2.67 Gpixels/sec
Edge Detection 3.1 Gpixels/sec 3.48 Gpixels/sec
Gaussian Blur 2.92 Gpixels/sec 3.52 Gpixels/sec
Feature Matching 0.33 Gpixels/sec 0.92 Gpixels/sec
Stereo Matching 161.8 Gpixels/sec 355.9 Gpixels/sec
Particle Physics 5395.1 FPS 9094.4 FPS
API OpenCL OpenCL
Sources: Geekbench [3], [4]

Cinebench 2024 GPU

Hardware benchmark using Maxon's Cinema 4D rendering engine
Cinebench 2024 GPU
RX 580
n/a
GTX 1660 Ti
3510

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
RX 580
8782
GTX 1660 Ti +43%
12581
G2D Mark 770 769
DirectX 11 60 FPS 103 FPS
DirectX 12 43 FPS 51 FPS
GPU Compute 3409 Ops/s 5020 Ops/s
Sources: PassMark [5], [6] – 33466 & 14541 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
RX 580
391.86
GTX 1660 Ti +102%
792.56
Sources: Blender [9], [10] – 91 & 795 samples
Add your GPU benchmark result

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
RX 580
7905
GTX 1660 Ti +36%
10788
GB6 ML Half Precision
RX 580
8166
GTX 1660 Ti +7%
8753
GB6 ML Quantized
RX 580
5642
GTX 1660 Ti +35%
7620
Image Classification (SP) 3143 4272
Image Segmentation (HP) 3955 6435
Image Super Resolution (Q) 7872 9635
Face Detection (HP) 11922 10867
Pose Estimation (Q) 41162 41061
Text Classification (SP) 1199 1737
Machine Translation (HP) 1773 3301
Object Detection (SP) 3620 5600
Depth Estimation (Q) 13995 18914
Style Transfer (SP) 84083 83427
Framework ONNX ONNX
Backend DirectML DirectML
Sources: Geekbench [9], [10]

Specifications

Technical specifications of Radeon RX 580 and GeForce GTX 1660 Ti

General

Vendor Amd Nvidia
Build Discrete Discrete
Released April 18, 2017 February 22, 2019
Launch price (MSRP) $229 $279
Case Desktop Desktop
Purpose Gaming Gaming
Segment High-end Entry-level
Architecture GCN 4.0 Turing
GPU Codename Polaris 20 TU116
Rival Equivalent - GeForce GTX 1060 - Radeon RX 5600 XT
Recommended CPU - Intel Core i5 8500 or above - Intel Core i5 9500 or above
Desktop GPU rating (83rd and 73rd place)

Graphics Processing Unit

Base Clock 1257 MHz 1500 MHz
Boost Clock 1340 MHz 1770 MHz
Shading Units 2304 1536
Texture Mapping Units (TMUs) 144 96
Render Output Units (ROPs) 32 48
Compute Units (Pipelines) - 24
Tensor Cores No No
Ray-tracing Cores No No
L1 Cache 16KB per cluster 64KB per cluster
L2 Cache 2MB shared 1536KB shared
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 43 GPixel/s 85 GPixel/s
Texture Fill Rate 193 GTexel/s 170 GTexel/s
FLOPS (FP32)
RX 580 +15%
6.2 TFLOPS
GTX 1660 Ti
5.4 TFLOPS

Physical

Interface PCIe 3.0 x16 PCIe 3.0 x16
TGP 185 W 120 W
Manufacturing GlobalFoundries TSMC
Fabrication Process 14 nm 12 nm
Die Size 232 mm² 284 mm²
Transistor Count 5 billion 6 billion
Transistor Density 21.55 MTr/mm² 21.13 MTr/mm²

Memory

Memory Type GDDR5 GDDR6
Memory Size 8 GB 6 GB
Memory Clock 2000 MHz 1500 MHz
Effective Memory Speed 8000 Mbps 12000 Mbps
Bus 256-bit 192-bit
ECC No No
Memory Bandwidth
RX 580
256 GB/s
GTX 1660 Ti +13%
288 GB/s

API

DirectX 12 12
Vulkan 1.3 1.3
OpenGL 4.6 4.6
OpenCL 2.1 3.0
CUDA - 7.5
Ray Tracing No No
DLSS No No
DisplayPort 1.4a 1.4a

Cast your vote

Choose between two graphics cards
10 (21.3%)
37 (78.7%)
Total votes: 47

Related comparisons

1. Radeon RX 580 vs GeForce GTX 1660 SUPER
2. Radeon RX 580 vs GeForce GTX 1650
3. Radeon RX 580 vs GeForce RTX 3050
4. Radeon RX 580 vs GeForce GTX 1060
5. GeForce GTX 1660 Ti vs GeForce GTX 1660 SUPER
6. GeForce GTX 1660 Ti vs GeForce RTX 4060
7. GeForce GTX 1660 Ti vs GeForce RTX 3060
8. GeForce GTX 1660 Ti vs GeForce RTX 3050

User opinions

You can share your opinion or ask a question in the comments below
🌐 Register your profile and become part of NanoReview community!
EnglishРусский