Radeon Pro Vega II Duo vs GeForce GTX 1660 Ti
Aggregate performance score
We've compared GeForce GTX 1660 Ti with Radeon Pro Vega II Duo, including specs and performance data.
Pro II Duo outperforms 1660 Ti by a small 8% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 204 | 178 |
| Place by popularity | 22 | not in top-100 |
| Cost-effectiveness evaluation | 31.20 | 2.40 |
| Power efficiency | 19.46 | 5.31 |
| Architecture | Turing (2018−2022) | GCN 5.1 (2018−2022) |
| GPU code name | TU116 | Vega 20 |
| Market segment | Desktop | Workstation |
| Release date | 22 February 2019 (7 years ago) | 3 June 2019 (6 years ago) |
| Launch price (MSRP) | $279 | $4,399 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
GTX 1660 Ti has 1200% better value for money than Pro Vega II Duo.
Performance to price scatter graph
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 1536 | 4096 ×2 |
| Core clock speed | 1500 MHz | 1400 MHz |
| Boost clock speed | 1770 MHz | 1720 MHz |
| Number of transistors | 6,600 million | 13,230 million |
| Manufacturing process technology | 12 nm | 7 nm |
| Power consumption (TDP) | 120 Watt | 475 Watt |
| Texture fill rate | 169.9 | 440.3 ×2 |
| Floating-point processing power | 5.437 TFLOPS | 14.09 TFLOPS ×2 |
| ROPs | 48 | 64 ×2 |
| TMUs | 96 | 256 ×2 |
| L1 Cache | 1.5 MB | 1 MB |
| L2 Cache | 1536 KB | 4 MB |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Interface | PCIe 3.0 x16 | Apple MPX |
| Length | 229 mm | no data |
| Width | 2-slot | Quad-slot |
| Supplementary power connectors | 1x 8-pin | None |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR6 | HBM2 |
| Maximum RAM amount | 6 GB | 32 GB ×2 |
| Memory bus width | 192 Bit | 4096 Bit ×2 |
| Memory clock speed | 1500 MHz | 1000 MHz |
| Memory bandwidth | 288.0 GB/s | 1.02 TB/s ×2 |
| Shared memory | - | - |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | 1x DVI, 1x HDMI, 1x DisplayPort | 1x HDMI 2.0b, 4x Thunderbolt |
| HDMI | + | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_1) | 12 (12_1) |
| Shader Model | 6.5 | 6.7 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 2.1 |
| Vulkan | 1.2.131 | 1.3 |
| CUDA | 7.5 | - |
Synthetic benchmarks
Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| Full HD | 104
−5.8%
| 110−120
+5.8%
|
| 1440p | 59
−1.7%
| 60−65
+1.7%
|
| 4K | 39
−2.6%
| 40−45
+2.6%
|
Cost per frame, $
| 1080p | 2.68
+1391%
| 39.99
−1391%
|
| 1440p | 4.73
+1450%
| 73.32
−1450%
|
| 4K | 7.15
+1437%
| 109.98
−1437%
|
- GTX 1660 Ti has 1391% lower cost per frame in 1080p
- GTX 1660 Ti has 1450% lower cost per frame in 1440p
- GTX 1660 Ti has 1437% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 170−180
−3.4%
|
180−190
+3.4%
|
| Cyberpunk 2077 | 78
−2.6%
|
80−85
+2.6%
|
| Resident Evil 4 Remake | 75−80
−2.6%
|
80−85
+2.6%
|
Full HD
Medium
| Battlefield 5 | 129
−0.8%
|
130−140
+0.8%
|
| Counter-Strike 2 | 170−180
−3.4%
|
180−190
+3.4%
|
| Cyberpunk 2077 | 71
−5.6%
|
75−80
+5.6%
|
| Far Cry 5 | 109
−0.9%
|
110−120
+0.9%
|
| Fortnite | 247
−5.3%
|
260−270
+5.3%
|
| Forza Horizon 4 | 131
−6.9%
|
140−150
+6.9%
|
| Forza Horizon 5 | 107
−2.8%
|
110−120
+2.8%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 200
−5%
|
210−220
+5%
|
| Valorant | 190−200
−3.1%
|
200−210
+3.1%
|
Full HD
High
| Battlefield 5 | 112
−7.1%
|
120−130
+7.1%
|
| Counter-Strike 2 | 170−180
−3.4%
|
180−190
+3.4%
|
| Counter-Strike: Global Offensive | 270−280
−5.1%
|
290−300
+5.1%
|
| Cyberpunk 2077 | 57
−5.3%
|
60−65
+5.3%
|
| Dota 2 | 181
−5%
|
190−200
+5%
|
| Far Cry 5 | 99
−1%
|
100−105
+1%
|
| Fortnite | 143
−4.9%
|
150−160
+4.9%
|
| Forza Horizon 4 | 122
−6.6%
|
130−140
+6.6%
|
| Forza Horizon 5 | 94
−6.4%
|
100−105
+6.4%
|
| Grand Theft Auto V | 119
−0.8%
|
120−130
+0.8%
|
| Metro Exodus | 55
+0%
|
55−60
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 150
−6.7%
|
160−170
+6.7%
|
| The Witcher 3: Wild Hunt | 116
−3.4%
|
120−130
+3.4%
|
| Valorant | 190−200
−3.1%
|
200−210
+3.1%
|
Full HD
Ultra
| Battlefield 5 | 102
−7.8%
|
110−120
+7.8%
|
| Cyberpunk 2077 | 46
+2.2%
|
45−50
−2.2%
|
| Dota 2 | 168
−7.1%
|
180−190
+7.1%
|
| Far Cry 5 | 94
−6.4%
|
100−105
+6.4%
|
| Forza Horizon 4 | 97
−3.1%
|
100−105
+3.1%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 129
−0.8%
|
130−140
+0.8%
|
| The Witcher 3: Wild Hunt | 62
−4.8%
|
65−70
+4.8%
|
| Valorant | 118
−1.7%
|
120−130
+1.7%
|
Full HD
Epic
| Fortnite | 117
−2.6%
|
120−130
+2.6%
|
1440p
High
| Counter-Strike 2 | 70−75
−5.6%
|
75−80
+5.6%
|
| Counter-Strike: Global Offensive | 210−220
−6.5%
|
230−240
+6.5%
|
| Grand Theft Auto V | 62
−4.8%
|
65−70
+4.8%
|
| Metro Exodus | 33
−6.1%
|
35−40
+6.1%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
−2.9%
|
180−190
+2.9%
|
| Valorant | 230−240
−4.3%
|
240−250
+4.3%
|
1440p
Ultra
| Battlefield 5 | 76
−5.3%
|
80−85
+5.3%
|
| Cyberpunk 2077 | 27
+0%
|
27−30
+0%
|
| Far Cry 5 | 67
−4.5%
|
70−75
+4.5%
|
| Forza Horizon 4 | 77
−3.9%
|
80−85
+3.9%
|
| The Witcher 3: Wild Hunt | 50−55
−3.8%
|
55−60
+3.8%
|
1440p
Epic
| Fortnite | 75
−6.7%
|
80−85
+6.7%
|
4K
High
| Counter-Strike 2 | 30−35
−6.1%
|
35−40
+6.1%
|
| Grand Theft Auto V | 56
−7.1%
|
60−65
+7.1%
|
| Metro Exodus | 21
+0%
|
21−24
+0%
|
| The Witcher 3: Wild Hunt | 43
−4.7%
|
45−50
+4.7%
|
| Valorant | 180−190
−7.5%
|
200−210
+7.5%
|
4K
Ultra
| Battlefield 5 | 43
−4.7%
|
45−50
+4.7%
|
| Counter-Strike 2 | 30−35
−6.1%
|
35−40
+6.1%
|
| Cyberpunk 2077 | 11
+10%
|
10−11
−10%
|
| Dota 2 | 94
−6.4%
|
100−105
+6.4%
|
| Far Cry 5 | 35
+0%
|
35−40
+0%
|
| Forza Horizon 4 | 51
−7.8%
|
55−60
+7.8%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 39
−2.6%
|
40−45
+2.6%
|
4K
Epic
| Fortnite | 25
+4.2%
|
24−27
−4.2%
|
This is how GTX 1660 Ti and Pro Vega II Duo compete in popular games:
- Pro Vega II Duo is 6% faster in 1080p
- Pro Vega II Duo is 2% faster in 1440p
- Pro Vega II Duo is 3% faster in 4K
Pros & cons summary
| Performance score | 30.32 | 32.74 |
| Recency | 22 February 2019 | 3 June 2019 |
| Maximum RAM amount | 6 GB | 32 GB |
| Chip lithography | 12 nm | 7 nm |
| Power consumption (TDP) | 120 Watt | 475 Watt |
GTX 1660 Ti has 296% lower power consumption.
Pro Vega II Duo, on the other hand, has a 8% higher aggregate performance score, an age advantage of 3 months, a 433% higher maximum VRAM amount, and a 71% more advanced lithography process.
Given the minimal performance differences, no clear winner can be declared between GeForce GTX 1660 Ti and Radeon Pro Vega II Duo.
Be aware that GeForce GTX 1660 Ti is a desktop graphics card while Radeon Pro Vega II Duo is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
