Radeon HD 7660G + HD 7670M Dual Graphics vs GeForce GTX 650
Aggregate performance score
We've compared GeForce GTX 650 with Radeon HD 7660G + HD 7670M Dual Graphics, including specs and performance data.
GTX 650 outperforms HD 7660G + HD 7670M Dual Graphics by a whopping 115% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 667 | 884 |
| Place by popularity | 71 | not in top-100 |
| Cost-effectiveness evaluation | 1.36 | no data |
| Power efficiency | 4.81 | no data |
| Architecture | Kepler (2012−2018) | Terascale 2 (2009−2015) |
| GPU code name | GK107 | no data |
| Market segment | Desktop | Laptop |
| Release date | 6 September 2012 (12 years ago) | 15 May 2012 (12 years ago) |
| Launch price (MSRP) | $109 | no data |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
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 | 384 | 862 |
| Core clock speed | 1058 MHz | 685 / 600 MHz |
| Number of transistors | 1,270 million | no data |
| Manufacturing process technology | 28 nm | 32 nm |
| Power consumption (TDP) | 64 Watt | no data |
| Texture fill rate | 33.86 | no data |
| Floating-point processing power | 0.8125 TFLOPS | no data |
| ROPs | 16 | no data |
| TMUs | 32 | no data |
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 | medium sized |
| Bus support | PCI Express 3.0 | no data |
| Interface | PCIe 3.0 x16 | no data |
| Length | 147 mm | no data |
| Height | 4.38" (11.1 cm) | no data |
| Width | 1-slot | no data |
| Supplementary power connectors | 1x 6-pin | no data |
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 | DDR3,GDDR5 |
| Maximum RAM amount | 2 GB | no data |
| Memory bus width | 128-bit GDDR5 | 128 Bit |
| Memory clock speed | 5.0 GB/s | 1800 MHz |
| Memory bandwidth | 80.0 GB/s | no data |
| Shared memory | - | - |
Connectivity and outputs
Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.
| Display Connectors | One Dual Link DVI-I, One Dual Link DVI-D, One Mini HDMI | no data |
| 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 compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (11_0) | 11 |
| Shader Model | 5.1 | no data |
| OpenGL | 4.3 | no data |
| OpenCL | 1.2 | no data |
| Vulkan | 1.1.126 | - |
| CUDA | + | - |
Synthetic benchmark performance
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.
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.
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 | 40−45
+111%
| 19
−111%
|
Cost per frame, $
| 1080p | 2.73 | no data |
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 5−6
+0%
|
5−6
+0%
|
| Counter-Strike 2 | 8−9
+0%
|
8−9
+0%
|
| Cyberpunk 2077 | 4−5
+0%
|
4−5
+0%
|
Full HD
Medium Preset
| Atomic Heart | 5−6
+0%
|
5−6
+0%
|
| Battlefield 5 | 5−6
+0%
|
5−6
+0%
|
| Counter-Strike 2 | 8−9
+0%
|
8−9
+0%
|
| Cyberpunk 2077 | 4−5
+0%
|
4−5
+0%
|
| Far Cry 5 | 2−3
+0%
|
2−3
+0%
|
| Fortnite | 9−10
+0%
|
9−10
+0%
|
| Forza Horizon 4 | 10−11
+0%
|
10−11
+0%
|
| Forza Horizon 5 | 2−3
+0%
|
2−3
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 10−12
+0%
|
10−12
+0%
|
| Valorant | 35−40
+0%
|
35−40
+0%
|
Full HD
High Preset
| Atomic Heart | 5−6
+0%
|
5−6
+0%
|
| Battlefield 5 | 5−6
+0%
|
5−6
+0%
|
| Counter-Strike 2 | 8−9
+0%
|
8−9
+0%
|
| Counter-Strike: Global Offensive | 40−45
+0%
|
40−45
+0%
|
| Cyberpunk 2077 | 4−5
+0%
|
4−5
+0%
|
| Dota 2 | 21−24
+0%
|
21−24
+0%
|
| Far Cry 5 | 2−3
+0%
|
2−3
+0%
|
| Fortnite | 9−10
+0%
|
9−10
+0%
|
| Forza Horizon 4 | 10−11
+0%
|
10−11
+0%
|
| Forza Horizon 5 | 2−3
+0%
|
2−3
+0%
|
| Grand Theft Auto V | 4−5
+0%
|
4−5
+0%
|
| Metro Exodus | 3−4
+0%
|
3−4
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 10−12
+0%
|
10−12
+0%
|
| The Witcher 3: Wild Hunt | 7−8
+0%
|
7−8
+0%
|
| Valorant | 35−40
+0%
|
35−40
+0%
|
Full HD
Ultra Preset
| Battlefield 5 | 5−6
+0%
|
5−6
+0%
|
| Counter-Strike 2 | 8−9
+0%
|
8−9
+0%
|
| Cyberpunk 2077 | 4−5
+0%
|
4−5
+0%
|
| Dota 2 | 21−24
+0%
|
21−24
+0%
|
| Far Cry 5 | 2−3
+0%
|
2−3
+0%
|
| Forza Horizon 4 | 10−11
+0%
|
10−11
+0%
|
| Forza Horizon 5 | 2−3
+0%
|
2−3
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 10−12
+0%
|
10−12
+0%
|
| The Witcher 3: Wild Hunt | 7−8
+0%
|
7−8
+0%
|
| Valorant | 35−40
+0%
|
35−40
+0%
|
Full HD
Epic Preset
| Fortnite | 9−10
+0%
|
9−10
+0%
|
1440p
High Preset
| Counter-Strike 2 | 2−3
+0%
|
2−3
+0%
|
| Counter-Strike: Global Offensive | 14−16
+0%
|
14−16
+0%
|
| Grand Theft Auto V | 0−1 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 14−16
+0%
|
14−16
+0%
|
| Valorant | 14−16
+0%
|
14−16
+0%
|
1440p
Ultra Preset
| Cyberpunk 2077 | 1−2
+0%
|
1−2
+0%
|
| Far Cry 5 | 3−4
+0%
|
3−4
+0%
|
| Forza Horizon 4 | 5−6
+0%
|
5−6
+0%
|
| Forza Horizon 5 | 1−2
+0%
|
1−2
+0%
|
| The Witcher 3: Wild Hunt | 3−4
+0%
|
3−4
+0%
|
1440p
Epic Preset
| Fortnite | 3−4
+0%
|
3−4
+0%
|
4K
High Preset
| Atomic Heart | 1−2
+0%
|
1−2
+0%
|
| Grand Theft Auto V | 14−16
+0%
|
14−16
+0%
|
| Valorant | 10−11
+0%
|
10−11
+0%
|
4K
Ultra Preset
| Cyberpunk 2077 | 0−1 | 0−1 |
| Dota 2 | 4−5
+0%
|
4−5
+0%
|
| Far Cry 5 | 2−3
+0%
|
2−3
+0%
|
| Forza Horizon 4 | 0−1 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 3−4
+0%
|
3−4
+0%
|
4K
Epic Preset
| Fortnite | 3−4
+0%
|
3−4
+0%
|
This is how GTX 650 and HD 7660G + HD 7670M Dual Graphics compete in popular games:
- GTX 650 is 111% faster in 1080p
All in all, in popular games:
- there's a draw in 56 tests (100%)
Pros & cons summary
| Performance score | 4.50 | 2.09 |
| Recency | 6 September 2012 | 15 May 2012 |
| Chip lithography | 28 nm | 32 nm |
GTX 650 has a 115.3% higher aggregate performance score, an age advantage of 3 months, and a 14.3% more advanced lithography process.
The GeForce GTX 650 is our recommended choice as it beats the Radeon HD 7660G + HD 7670M Dual Graphics in performance tests.
Be aware that GeForce GTX 650 is a desktop card while Radeon HD 7660G + HD 7670M Dual Graphics is a notebook one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
