Quadro RTX 3000 Mobile vs GeForce GTX 675M SLI

Place in the ranking	498	213
Place by popularity	not in top-100	not in top-100
Power efficiency	2.99	22.64
Architecture	Fermi (2010−2014)	Turing (2018−2022)
GPU code name	N12E-GTX2	TU106
Market segment	Laptop	Mobile workstation
Release date	6 January 2011 (14 years ago)	27 May 2019 (5 years ago)

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	768	2304
Core clock speed	620 MHz	945 MHz
Boost clock speed	no data	1380 MHz
Number of transistors	no data	10,800 million
Manufacturing process technology	40 nm	12 nm
Power consumption (TDP)	2x 100 Watt	80 Watt
Texture fill rate	no data	198.7
Floating-point processing power	no data	6.359 TFLOPS
ROPs	no data	64
TMUs	no data	144
Tensor Cores	no data	288
Ray Tracing Cores	no data	36

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	large
Interface	no data	PCIe 3.0 x16
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	GDDR6
Maximum RAM amount	no data	6 GB
Memory bus width	256 Bit	256 Bit
Memory clock speed	3000 MHz	1750 MHz
Memory bandwidth	no data	448.0 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 data	No outputs
G-SYNC support	-	+

Supported technologies

Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.

Optimus	+	-
VR Ready	no data	+

API compatibility

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	11	12 Ultimate (12_1)
Shader Model	no data	6.5
OpenGL	no data	4.6
OpenCL	no data	1.2
Vulkan	-	1.2.131
CUDA	+	7.5

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.

GTX 675M SLI 8.68

RTX 3000 Mobile 26.31
+203%

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.

GTX 675M SLI 6407

RTX 3000 Mobile 19879
+210%

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.

GTX 675M SLI 18405

RTX 3000 Mobile 50309
+173%

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	30−35 −243%	103 +243%
4K	27−30 −226%	88 +226%

FPS performance in popular games

Full HD
Low Preset

Counter-Strike 2	16−18 −188%	45−50 +188%
Cyberpunk 2077	16−18 −218%	50−55 +218%
Elden Ring	24−27 −263%	85−90 +263%

Full HD
Medium Preset

Battlefield 5	27−30 −186%	80−85 +186%
Counter-Strike 2	16−18 −188%	45−50 +188%
Cyberpunk 2077	16−18 −218%	50−55 +218%
Forza Horizon 4	35−40 −231%	110−120 +231%
Metro Exodus	21−24 −296%	91 +296%
Red Dead Redemption 2	24−27 −138%	55−60 +138%
Valorant	30−35 −239%	100−110 +239%

Full HD
High Preset

Battlefield 5	27−30 −186%	80−85 +186%
Counter-Strike 2	16−18 −188%	45−50 +188%
Cyberpunk 2077	16−18 −218%	50−55 +218%
Dota 2	30−35 −41.9%	44 +41.9%
Elden Ring	24−27 −263%	85−90 +263%
Far Cry 5	35−40 −132%	86 +132%
Fortnite	50−55 −155%	130−140 +155%
Forza Horizon 4	35−40 −231%	110−120 +231%
Grand Theft Auto V	30−35 −187%	85−90 +187%
Metro Exodus	21−24 −87%	43 +87%
PLAYERUNKNOWN'S BATTLEGROUNDS	65−70 −61.8%	110 +61.8%
Red Dead Redemption 2	24−27 −138%	55−60 +138%
The Witcher 3: Wild Hunt	24−27 −231%	85−90 +231%
Valorant	30−35 −239%	100−110 +239%
World of Tanks	120−130 −104%	260−270 +104%

Full HD
Ultra Preset

Battlefield 5	27−30 −186%	80−85 +186%
Counter-Strike 2	16−18 −188%	45−50 +188%
Cyberpunk 2077	16−18 −218%	50−55 +218%
Dota 2	30−35 −290%	121 +290%
Far Cry 5	35−40 −114%	75−80 +114%
Forza Horizon 4	35−40 −231%	110−120 +231%
PLAYERUNKNOWN'S BATTLEGROUNDS	65−70 −138%	160−170 +138%
Valorant	30−35 −239%	100−110 +239%

1440p
High Preset

Dota 2	10−11 −350%	45−50 +350%
Elden Ring	12−14 −292%	45−50 +292%
Grand Theft Auto V	10−12 −309%	45−50 +309%
PLAYERUNKNOWN'S BATTLEGROUNDS	40−45 −317%	170−180 +317%
Red Dead Redemption 2	7−8 −243%	24−27 +243%
World of Tanks	60−65 −175%	170−180 +175%

1440p
Ultra Preset

Battlefield 5	16−18 −231%	50−55 +231%
Counter-Strike 2	10−11 −130%	21−24 +130%
Cyberpunk 2077	6−7 −283%	21−24 +283%
Far Cry 5	18−20 −333%	75−80 +333%
Forza Horizon 4	18−20 −289%	70−75 +289%
Metro Exodus	14−16 −300%	60−65 +300%
The Witcher 3: Wild Hunt	10−11 −290%	35−40 +290%
Valorant	21−24 −227%	70−75 +227%

4K
High Preset

Counter-Strike 2	3−4 −700%	24−27 +700%
Dota 2	18−20 −142%	45−50 +142%
Elden Ring	5−6 −320%	21−24 +320%
Grand Theft Auto V	18−20 −142%	45−50 +142%
Metro Exodus	4−5 −400%	20−22 +400%
PLAYERUNKNOWN'S BATTLEGROUNDS	24−27 −224%	80−85 +224%
Red Dead Redemption 2	6−7 −183%	16−18 +183%
The Witcher 3: Wild Hunt	18−20 −142%	45−50 +142%

4K
Ultra Preset

Battlefield 5	7−8 −300%	27−30 +300%
Counter-Strike 2	3−4 −700%	24−27 +700%
Cyberpunk 2077	2−3 −350%	9−10 +350%
Dota 2	18−20 −363%	88 +363%
Far Cry 5	10−11 −250%	35−40 +250%
Fortnite	9−10 −267%	30−35 +267%
Forza Horizon 4	10−11 −310%	40−45 +310%
Valorant	8−9 −338%	35−40 +338%

This is how GTX 675M SLI and RTX 3000 Mobile compete in popular games:

RTX 3000 Mobile is 243% faster in 1080p
RTX 3000 Mobile is 226% faster in 4K

Here's the range of performance differences observed across popular games:

in Counter-Strike 2, with 4K resolution and the High Preset, the RTX 3000 Mobile is 700% faster.

All in all, in popular games:

Without exception, RTX 3000 Mobile surpassed GTX 675M SLI in all 63 of our tests.

Pros & cons summary

Performance score	8.68	26.31
Recency	6 January 2011	27 May 2019
Chip lithography	40 nm	12 nm
Power consumption (TDP)	2 Watt	80 Watt

GTX 675M SLI has 3900% lower power consumption.

RTX 3000 Mobile, on the other hand, has a 203.1% higher aggregate performance score, an age advantage of 8 years, and a 233.3% more advanced lithography process.

The Quadro RTX 3000 Mobile is our recommended choice as it beats the GeForce GTX 675M SLI in performance tests.

Be aware that GeForce GTX 675M SLI is a notebook graphics card while Quadro RTX 3000 Mobile is a mobile workstation one.

Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.