Radeon Pro Vega 16 vs GeForce GTX 660 Ti
Aggregate performance score
We've compared GeForce GTX 660 Ti with Radeon Pro Vega 16, including specs and performance data.
Pro 16 outperforms 660 Ti by a small 9% 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 | 472 | 450 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 2.63 | no data |
| Power efficiency | 5.37 | 11.72 |
| Architecture | Kepler (2012−2018) | GCN 5.0 (2017−2020) |
| GPU code name | GK104 | Vega 12 |
| Market segment | Desktop | Mobile workstation |
| Release date | 16 August 2012 (13 years ago) | 14 November 2018 (6 years ago) |
| Launch price (MSRP) | $299 | no data |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
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 | 1344 | 1024 |
| Core clock speed | 915 MHz | 815 MHz |
| Boost clock speed | 980 MHz | 1190 MHz |
| Number of transistors | 3,540 million | no data |
| Manufacturing process technology | 28 nm | 14 nm |
| Power consumption (TDP) | 150 Watt | 75 Watt |
| Texture fill rate | 109.8 | 76.16 |
| Floating-point processing power | 2.634 TFLOPS | 2.437 TFLOPS |
| ROPs | 24 | 32 |
| TMUs | 112 | 64 |
| L1 Cache | 112 KB | 256 KB |
| L2 Cache | 384 KB | 1024 KB |
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).
| Laptop size | no data | large |
| Bus support | PCI Express 3.0 | no data |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Length | 241 mm | no data |
| Height | 4.376" (11.1 cm) | no data |
| Width | 2-slot | no data |
| Supplementary power connectors | 2x 6-pin | no data |
| SLI options | + | - |
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 | GDDR5 | HBM2 |
| Maximum RAM amount | 2 GB | 4 GB |
| Memory bus width | 192-bit GDDR5 | 1024 Bit |
| Memory clock speed | 6.0 GB/s | 1200 MHz |
| Memory bandwidth | 144.2 GB/s | 307.2 GB/s |
| 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 | One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort | No outputs |
| Multi monitor support | 4 displays | no data |
| HDMI | + | - |
| HDCP | + | - |
| Maximum VGA resolution | 2048x1536 | no data |
| Audio input for HDMI | Internal | no data |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| 3D Blu-Ray | + | - |
| 3D Gaming | + | - |
| 3D Vision | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (11_0) | 12 (12_1) |
| Shader Model | 5.1 | 6.3 |
| OpenGL | 4.3 | 4.6 |
| OpenCL | 1.2 | 2.0 |
| Vulkan | 1.1.126 | 1.2.131 |
| CUDA | + | - |
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.
3DMark 11 Performance GPU
3DMark 11 is an obsolete DirectX 11 benchmark by Futuremark. It used four tests based on two scenes, one being few submarines exploring the submerged wreck of a sunken ship, the other is an abandoned temple deep in the jungle. All the tests are heavy with volumetric lighting and tessellation, and despite being done in 1280x720 resolution, are relatively taxing. Discontinued in January 2020, 3DMark 11 is now superseded by Time Spy.
3DMark Fire Strike Graphics
Fire Strike is a DirectX 11 benchmark for gaming PCs. It features two separate tests displaying a fight between a humanoid and a fiery creature made of lava. Using 1920x1080 resolution, Fire Strike shows off some realistic graphics and is quite taxing on hardware.
3DMark Cloud Gate GPU
Cloud Gate is an outdated DirectX 11 feature level 10 benchmark that was used for home PCs and basic notebooks. It displays a few scenes of some weird space teleportation device launching spaceships into unknown, using fixed resolution of 1280x720. Just like Ice Storm benchmark, it has been discontinued in January 2020 and replaced by 3DMark Night Raid.
GeekBench 5 OpenCL
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses OpenCL API by Khronos Group.
GeekBench 5 Vulkan
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses Vulkan API by AMD & Khronos Group.
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 | 77
+30.5%
| 59
−30.5%
|
| 4K | 30−35
−26.7%
| 38
+26.7%
|
Cost per frame, $
| 1080p | 3.88 | no data |
| 4K | 9.97 | no data |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 55−60
−10.3%
|
60−65
+10.3%
|
| Cyberpunk 2077 | 21−24
−9.1%
|
24−27
+9.1%
|
| Hogwarts Legacy | 18−20
−10.5%
|
21−24
+10.5%
|
Full HD
Medium
| Battlefield 5 | 45−50
−8.5%
|
50−55
+8.5%
|
| Counter-Strike 2 | 55−60
−10.3%
|
60−65
+10.3%
|
| Cyberpunk 2077 | 21−24
−9.1%
|
24−27
+9.1%
|
| Far Cry 5 | 35−40
−8.6%
|
35−40
+8.6%
|
| Fortnite | 60−65
−7.8%
|
65−70
+7.8%
|
| Forza Horizon 4 | 45−50
−8.7%
|
50−55
+8.7%
|
| Forza Horizon 5 | 30−35
−9.1%
|
35−40
+9.1%
|
| Hogwarts Legacy | 18−20
−10.5%
|
21−24
+10.5%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 35−40
−7.7%
|
40−45
+7.7%
|
| Valorant | 95−100
−6.1%
|
100−110
+6.1%
|
Full HD
High
| Battlefield 5 | 45−50
−8.5%
|
50−55
+8.5%
|
| Counter-Strike 2 | 55−60
−10.3%
|
60−65
+10.3%
|
| Counter-Strike: Global Offensive | 192
+14.3%
|
160−170
−14.3%
|
| Cyberpunk 2077 | 21−24
−9.1%
|
24−27
+9.1%
|
| Dota 2 | 75−80
+0%
|
75
+0%
|
| Far Cry 5 | 35−40
−8.6%
|
35−40
+8.6%
|
| Fortnite | 60−65
−7.8%
|
65−70
+7.8%
|
| Forza Horizon 4 | 45−50
−8.7%
|
50−55
+8.7%
|
| Forza Horizon 5 | 30−35
−9.1%
|
35−40
+9.1%
|
| Grand Theft Auto V | 40−45
−10%
|
40−45
+10%
|
| Hogwarts Legacy | 18−20
−10.5%
|
21−24
+10.5%
|
| Metro Exodus | 21−24
−9.1%
|
24−27
+9.1%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 35−40
−7.7%
|
40−45
+7.7%
|
| The Witcher 3: Wild Hunt | 27−30
−10.7%
|
30−35
+10.7%
|
| Valorant | 95−100
−6.1%
|
100−110
+6.1%
|
Full HD
Ultra
| Battlefield 5 | 45−50
−8.5%
|
50−55
+8.5%
|
| Cyberpunk 2077 | 21−24
−9.1%
|
24−27
+9.1%
|
| Dota 2 | 75−80
+4.2%
|
72
−4.2%
|
| Far Cry 5 | 35−40
−8.6%
|
35−40
+8.6%
|
| Forza Horizon 4 | 45−50
−8.7%
|
50−55
+8.7%
|
| Hogwarts Legacy | 18−20
−10.5%
|
21−24
+10.5%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 35−40
−7.7%
|
40−45
+7.7%
|
| The Witcher 3: Wild Hunt | 27−30
+3.7%
|
27
−3.7%
|
| Valorant | 95−100
−6.1%
|
100−110
+6.1%
|
Full HD
Epic
| Fortnite | 60−65
−7.8%
|
65−70
+7.8%
|
1440p
High
| Counter-Strike 2 | 20−22
−10%
|
21−24
+10%
|
| Counter-Strike: Global Offensive | 80−85
−8.6%
|
85−90
+8.6%
|
| Grand Theft Auto V | 16−18
−12.5%
|
18−20
+12.5%
|
| Metro Exodus | 12−14
−16.7%
|
14−16
+16.7%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 65−70
−33.8%
|
85−90
+33.8%
|
| Valorant | 110−120
−6.8%
|
120−130
+6.8%
|
1440p
Ultra
| Battlefield 5 | 27−30
−10.7%
|
30−35
+10.7%
|
| Cyberpunk 2077 | 9−10
−11.1%
|
10−11
+11.1%
|
| Far Cry 5 | 21−24
−8.7%
|
24−27
+8.7%
|
| Forza Horizon 4 | 24−27
−12%
|
27−30
+12%
|
| Hogwarts Legacy | 10−12
−18.2%
|
12−14
+18.2%
|
| The Witcher 3: Wild Hunt | 14−16
−13.3%
|
16−18
+13.3%
|
1440p
Epic
| Fortnite | 21−24
−8.7%
|
24−27
+8.7%
|
4K
High
| Counter-Strike 2 | 5−6
−40%
|
7−8
+40%
|
| Grand Theft Auto V | 21−24
−4.5%
|
21−24
+4.5%
|
| Hogwarts Legacy | 5−6
−20%
|
6−7
+20%
|
| Metro Exodus | 6−7
−33.3%
|
8−9
+33.3%
|
| The Witcher 3: Wild Hunt | 12−14
−15.4%
|
14−16
+15.4%
|
| Valorant | 55−60
−8.8%
|
60−65
+8.8%
|
4K
Ultra
| Battlefield 5 | 14−16
−14.3%
|
16−18
+14.3%
|
| Counter-Strike 2 | 5−6
−40%
|
7−8
+40%
|
| Cyberpunk 2077 | 3−4
−33.3%
|
4−5
+33.3%
|
| Dota 2 | 35−40
+2.6%
|
38
−2.6%
|
| Far Cry 5 | 10−12
−9.1%
|
12−14
+9.1%
|
| Forza Horizon 4 | 18−20
−11.1%
|
20−22
+11.1%
|
| Hogwarts Legacy | 5−6
−20%
|
6−7
+20%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 10−11
−10%
|
10−12
+10%
|
4K
Epic
| Fortnite | 10−11
−10%
|
10−12
+10%
|
This is how GTX 660 Ti and Pro Vega 16 compete in popular games:
- GTX 660 Ti is 31% faster in 1080p
- Pro Vega 16 is 27% faster in 4K
Here's the range of performance differences observed across popular games:
- in Counter-Strike: Global Offensive, with 1080p resolution and the High Preset, the GTX 660 Ti is 14% faster.
- in Counter-Strike 2, with 4K resolution and the High Preset, the Pro Vega 16 is 40% faster.
All in all, in popular games:
- GTX 660 Ti performs better in 4 tests (6%)
- Pro Vega 16 performs better in 61 tests (92%)
- there's a draw in 1 test (2%)
Pros & cons summary
| Performance score | 9.98 | 10.88 |
| Recency | 16 August 2012 | 14 November 2018 |
| Maximum RAM amount | 2 GB | 4 GB |
| Chip lithography | 28 nm | 14 nm |
| Power consumption (TDP) | 150 Watt | 75 Watt |
Pro Vega 16 has a 9% higher aggregate performance score, an age advantage of 6 years, a 100% higher maximum VRAM amount, a 100% more advanced lithography process, and 100% lower power consumption.
Given the minimal performance differences, no clear winner can be declared between GeForce GTX 660 Ti and Radeon Pro Vega 16.
Be aware that GeForce GTX 660 Ti is a desktop graphics card while Radeon Pro Vega 16 is a mobile workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
