GeForce RTX 3090 vs GTX 660M
Aggregate performance score
We've compared GeForce GTX 660M with GeForce RTX 3090, including specs and performance data.
RTX 3090 outperforms GTX 660M by a whopping 1748% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 705 | 24 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 14.90 |
| Power efficiency | 5.23 | 13.80 |
| Architecture | Kepler (2012−2018) | Ampere (2020−2024) |
| GPU code name | GK107 | GA102 |
| Market segment | Laptop | Desktop |
| Release date | 22 March 2012 (12 years ago) | 1 September 2020 (4 years ago) |
| Launch price (MSRP) | no data | $1,499 |
Cost-effectiveness evaluation
Performance to price ratio. The higher, the better.
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 | 10496 |
| Core clock speed | 835 MHz | 1395 MHz |
| Boost clock speed | 950 MHz | 1695 MHz |
| Number of transistors | 1,270 million | 28,300 million |
| Manufacturing process technology | 28 nm | 8 nm |
| Power consumption (TDP) | 50 Watt | 350 Watt |
| Texture fill rate | 30.40 | 556.0 |
| Floating-point processing power | 0.7296 TFLOPS | 35.58 TFLOPS |
| ROPs | 16 | 112 |
| TMUs | 32 | 328 |
| Tensor Cores | no data | 328 |
| Ray Tracing Cores | no data | 82 |
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 | large | no data |
| Bus support | PCI Express 2.0, PCI Express 3.0 | no data |
| Interface | MXM-B (3.0) | PCIe 4.0 x16 |
| Length | no data | 336 mm |
| Width | no data | 3-slot |
| Supplementary power connectors | no data | 1x 12-pin |
| 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 | GDDR6X |
| Maximum RAM amount | 1 GB | 24 GB |
| Memory bus width | 128bit | 384 Bit |
| Memory clock speed | 2000 MHz | 1219 MHz |
| Memory bandwidth | 64.0 GB/s | 936.2 GB/s |
| 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 | No outputs | 1x HDMI, 3x DisplayPort |
| HDMI | + | + |
| HDCP | + | - |
| Maximum VGA resolution | Up to 2048x1536 | no data |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| Optimus | + | - |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 API | 12 Ultimate (12_2) |
| Shader Model | 5.1 | 6.5 |
| OpenGL | 4.5 | 4.6 |
| OpenCL | 1.1 | 2.0 |
| Vulkan | 1.1.126 | 1.2 |
| CUDA | + | 8.5 |
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. We are regularly improving our combining algorithms, but if you find some perceived inconsistencies, feel free to speak up in comments section, we usually fix problems quickly.
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 Vantage Performance
3DMark Vantage is an outdated DirectX 10 benchmark using 1280x1024 screen resolution. It taxes the graphics card with two scenes, one depicting a girl escaping some militarized base located within a sea cave, the other displaying a space fleet attack on a defenseless planet. It was discontinued in April 2017, and Time Spy benchmark is now recommended to be used instead.
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.
GeekBench 5 CUDA
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 CUDA API by NVIDIA.
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:
| 900p | 32
−1619%
| 550−600
+1619%
|
| Full HD | 35
−480%
| 203
+480%
|
| 1200p | 38
−1742%
| 700−750
+1742%
|
| 1440p | 7−8
−1771%
| 131
+1771%
|
| 4K | 4−5
−2150%
| 90
+2150%
|
Cost per frame, $
| 1080p | no data | 7.38 |
| 1440p | no data | 11.44 |
| 4K | no data | 16.66 |
FPS performance in popular games
Full HD
Low Preset
| Cyberpunk 2077 | 7−8
−2857%
|
207
+2857%
|
Full HD
Medium Preset
| Assassin's Creed Odyssey | 10−12
−1345%
|
159
+1345%
|
| Assassin's Creed Valhalla | 3−4
−3700%
|
114
+3700%
|
| Battlefield 5 | 8−9
−2675%
|
220−230
+2675%
|
| Call of Duty: Modern Warfare | 8−9
−1388%
|
110−120
+1388%
|
| Cyberpunk 2077 | 7−8
−2414%
|
176
+2414%
|
| Far Cry 5 | 8−9
−1363%
|
110−120
+1363%
|
| Far Cry New Dawn | 10−11
−1590%
|
160−170
+1590%
|
| Forza Horizon 4 | 21−24
−982%
|
230−240
+982%
|
| Hitman 3 | 9−10
−1200%
|
117
+1200%
|
| Horizon Zero Dawn | 24−27
−873%
|
250−260
+873%
|
| Metro Exodus | 7−8
−1957%
|
144
+1957%
|
| Red Dead Redemption 2 | 9−10
−1344%
|
130
+1344%
|
| Shadow of the Tomb Raider | 14−16
−1986%
|
290−300
+1986%
|
| Watch Dogs: Legion | 40−45
−376%
|
200
+376%
|
Full HD
High Preset
| Assassin's Creed Odyssey | 10−12
−2145%
|
247
+2145%
|
| Assassin's Creed Valhalla | 3−4
−3400%
|
105
+3400%
|
| Battlefield 5 | 8−9
−2675%
|
220−230
+2675%
|
| Call of Duty: Modern Warfare | 8−9
−1388%
|
110−120
+1388%
|
| Cyberpunk 2077 | 7−8
−2057%
|
151
+2057%
|
| Far Cry 5 | 8−9
−1363%
|
110−120
+1363%
|
| Far Cry New Dawn | 10−11
−1590%
|
160−170
+1590%
|
| Forza Horizon 4 | 21−24
−982%
|
230−240
+982%
|
| Hitman 3 | 9−10
−1200%
|
117
+1200%
|
| Horizon Zero Dawn | 24−27
−873%
|
250−260
+873%
|
| Metro Exodus | 7−8
−1957%
|
144
+1957%
|
| Red Dead Redemption 2 | 9−10
−1256%
|
120−130
+1256%
|
| Shadow of the Tomb Raider | 14−16
−2771%
|
402
+2771%
|
| The Witcher 3: Wild Hunt | 14−16
−893%
|
140−150
+893%
|
| Watch Dogs: Legion | 40−45
−374%
|
199
+374%
|
Full HD
Ultra Preset
| Assassin's Creed Odyssey | 10−12
−882%
|
108
+882%
|
| Assassin's Creed Valhalla | 3−4
−2933%
|
91
+2933%
|
| Call of Duty: Modern Warfare | 8−9
−1388%
|
110−120
+1388%
|
| Cyberpunk 2077 | 7−8
−1814%
|
134
+1814%
|
| Far Cry 5 | 8−9
−1363%
|
110−120
+1363%
|
| Forza Horizon 4 | 21−24
−886%
|
217
+886%
|
| Hitman 3 | 9−10
−1189%
|
116
+1189%
|
| Horizon Zero Dawn | 24−27
−1035%
|
295
+1035%
|
| Shadow of the Tomb Raider | 14−16
−2407%
|
351
+2407%
|
| The Witcher 3: Wild Hunt | 14−16
−1107%
|
181
+1107%
|
| Watch Dogs: Legion | 40−45
−155%
|
107
+155%
|
Full HD
Epic Preset
| Red Dead Redemption 2 | 9−10
−1333%
|
129
+1333%
|
1440p
High Preset
| Battlefield 5 | 7−8
−2257%
|
160−170
+2257%
|
| Far Cry New Dawn | 6−7
−1733%
|
110−120
+1733%
|
1440p
Ultra Preset
| Assassin's Creed Odyssey | 3−4
−3000%
|
93
+3000%
|
| Call of Duty: Modern Warfare | 3−4
−2600%
|
80−85
+2600%
|
| Cyberpunk 2077 | 2−3
−4550%
|
93
+4550%
|
| Far Cry 5 | 4−5
−1925%
|
80−85
+1925%
|
| Forza Horizon 4 | 3−4
−8933%
|
270−280
+8933%
|
| Hitman 3 | 8−9
−1338%
|
115
+1338%
|
| Horizon Zero Dawn | 9−10
−2489%
|
233
+2489%
|
| The Witcher 3: Wild Hunt | 3−4
−4967%
|
152
+4967%
|
| Watch Dogs: Legion | 21−24
−783%
|
203
+783%
|
1440p
Epic Preset
| Red Dead Redemption 2 | 7−8
−1714%
|
127
+1714%
|
4K
High Preset
| Battlefield 5 | 2−3
−4250%
|
85−90
+4250%
|
| Far Cry New Dawn | 2−3
−3350%
|
65−70
+3350%
|
| Metro Exodus | 0−1 | 141 |
4K
Ultra Preset
| Assassin's Creed Odyssey | 3−4
−2233%
|
70
+2233%
|
| Assassin's Creed Valhalla | 2−3
−2750%
|
57
+2750%
|
| Call of Duty: Modern Warfare | 1−2
−5000%
|
50−55
+5000%
|
| Cyberpunk 2077 | 0−1 | 46 |
| Far Cry 5 | 2−3
−2400%
|
50−55
+2400%
|
| Forza Horizon 4 | 2−3
−7550%
|
153
+7550%
|
| Watch Dogs: Legion | 1−2
−5900%
|
60
+5900%
|
4K
Epic Preset
| Red Dead Redemption 2 | 5−6
−2120%
|
111
+2120%
|
1440p
Ultra Preset
| Assassin's Creed Valhalla | 79
+0%
|
79
+0%
|
| Metro Exodus | 139
+0%
|
139
+0%
|
| Shadow of the Tomb Raider | 266
+0%
|
266
+0%
|
4K
High Preset
| Hitman 3 | 83
+0%
|
83
+0%
|
| Horizon Zero Dawn | 220−230
+0%
|
220−230
+0%
|
| The Witcher 3: Wild Hunt | 153
+0%
|
153
+0%
|
4K
Ultra Preset
| Shadow of the Tomb Raider | 159
+0%
|
159
+0%
|
This is how GTX 660M and RTX 3090 compete in popular games:
- RTX 3090 is 1619% faster in 900p
- RTX 3090 is 480% faster in 1080p
- RTX 3090 is 1742% faster in 1200p
- RTX 3090 is 1771% faster in 1440p
- RTX 3090 is 2150% faster in 4K
Here's the range of performance differences observed across popular games:
- in Forza Horizon 4, with 1440p resolution and the Ultra Preset, the RTX 3090 is 8933% faster.
All in all, in popular games:
- RTX 3090 is ahead in 63 tests (90%)
- there's a draw in 7 tests (10%)
Pros & cons summary
| Performance score | 3.75 | 69.30 |
| Recency | 22 March 2012 | 1 September 2020 |
| Maximum RAM amount | 1 GB | 24 GB |
| Chip lithography | 28 nm | 8 nm |
| Power consumption (TDP) | 50 Watt | 350 Watt |
GTX 660M has 600% lower power consumption.
RTX 3090, on the other hand, has a 1748% higher aggregate performance score, an age advantage of 8 years, a 2300% higher maximum VRAM amount, and a 250% more advanced lithography process.
The GeForce RTX 3090 is our recommended choice as it beats the GeForce GTX 660M in performance tests.
Be aware that GeForce GTX 660M is a notebook card while GeForce RTX 3090 is a desktop one.
Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.
Comparisons with similar GPUs
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
