RTX 4000 SFF Ada Generation vs GeForce GTX 1660 Ti

Place in the ranking	165	52
Place by popularity	27	not in top-100
Cost-effectiveness evaluation	42.62	no data
Power efficiency	19.31	53.19
Architecture	Turing (2018−2022)	Ada Lovelace (2022−2024)
GPU code name	TU116	AD104
Market segment	Desktop	Workstation
Release date	22 February 2019 (5 years ago)	21 March 2023 (1 year ago)
Launch price (MSRP)	$279	no data

Cost-effectiveness evaluation

The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.

no data

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	6144
Core clock speed	1500 MHz	720 MHz
Boost clock speed	1770 MHz	1560 MHz
Number of transistors	6,600 million	35,800 million
Manufacturing process technology	12 nm	5 nm
Power consumption (TDP)	120 Watt	70 Watt
Texture fill rate	169.9	299.5
Floating-point processing power	5.437 TFLOPS	19.17 TFLOPS
ROPs	48	80
TMUs	96	192
Tensor Cores	no data	192
Ray Tracing Cores	no data	48

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	PCIe 4.0 x16
Length	229 mm	168 mm
Width	2-slot	2-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	GDDR6
Maximum RAM amount	6 GB	20 GB
Memory bus width	192 Bit	160 Bit
Memory clock speed	1500 MHz	1750 MHz
Memory bandwidth	288.0 GB/s	280.0 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	1x DVI, 1x HDMI, 1x DisplayPort	4x mini-DisplayPort 1.4a
HDMI	+	-

API and SDK compatibility

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

DirectX	12 (12_1)	12 Ultimate (12_2)
Shader Model	6.5	6.8
OpenGL	4.6	4.6
OpenCL	1.2	3.0
Vulkan	1.2.131	1.3
CUDA	7.5	8.9

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 1660 Ti 32.42

RTX 4000 SFF Ada Generation 52.10
+60.7%

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.

GTX 1660 Ti 12906

RTX 4000 SFF Ada Generation 20741
+60.7%

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.

GTX 1660 Ti 60890

RTX 4000 SFF Ada Generation 124441
+104%

GeekBench 5 Vulkan

GTX 1660 Ti 57928

RTX 4000 SFF Ada Generation 106433
+83.7%

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	103 −55.3%	160−170 +55.3%
1440p	60 −58.3%	95−100 +58.3%
4K	39 −53.8%	60−65 +53.8%

Cost per frame, $

1080p	2.71	no data
1440p	4.65	no data
4K	7.15	no data

FPS performance in popular games

Full HD
Low Preset

Counter-Strike 2	65−70 −51.5%	100−105 +51.5%
Cyberpunk 2077	78 −53.8%	120−130 +53.8%

Full HD
Medium Preset

Battlefield 5	90 −55.6%	140−150 +55.6%
Counter-Strike 2	65−70 −51.5%	100−105 +51.5%
Cyberpunk 2077	36 −52.8%	55−60 +52.8%
Forza Horizon 4	156 −60.3%	250−260 +60.3%
Forza Horizon 5	94 −59.6%	150−160 +59.6%
Metro Exodus	98 −53.1%	150−160 +53.1%
Red Dead Redemption 2	119 −59.7%	190−200 +59.7%
Valorant	161 −55.3%	250−260 +55.3%

Full HD
High Preset

Battlefield 5	123 −54.5%	190−200 +54.5%
Counter-Strike 2	65−70 −51.5%	100−105 +51.5%
Cyberpunk 2077	28 −42.9%	40−45 +42.9%
Dota 2	140 −57.1%	220−230 +57.1%
Far Cry 5	118 −52.5%	180−190 +52.5%
Fortnite	134 −56.7%	210−220 +56.7%
Forza Horizon 4	127 −57.5%	200−210 +57.5%
Forza Horizon 5	72 −52.8%	110−120 +52.8%
Grand Theft Auto V	119 −59.7%	190−200 +59.7%
Metro Exodus	68 −47.1%	100−105 +47.1%
PLAYERUNKNOWN'S BATTLEGROUNDS	180−190 −60.4%	300−310 +60.4%
Red Dead Redemption 2	45 −55.6%	70−75 +55.6%
The Witcher 3: Wild Hunt	110−120 −56.5%	180−190 +56.5%
Valorant	82 −58.5%	130−140 +58.5%
World of Tanks	270−280 −43.9%	400−450 +43.9%

Full HD
Ultra Preset

Battlefield 5	78 −53.8%	120−130 +53.8%
Counter-Strike 2	65−70 −51.5%	100−105 +51.5%
Cyberpunk 2077	23 −52.2%	35−40 +52.2%
Dota 2	168 −54.8%	260−270 +54.8%
Far Cry 5	90−95 −55.6%	140−150 +55.6%
Forza Horizon 4	110 −54.5%	170−180 +54.5%
Forza Horizon 5	66 −51.5%	100−105 +51.5%
PLAYERUNKNOWN'S BATTLEGROUNDS	98 −53.1%	150−160 +53.1%
Valorant	118 −52.5%	180−190 +52.5%

1440p
High Preset

Counter-Strike 2	27−30 −42.9%	40−45 +42.9%
Dota 2	62 −53.2%	95−100 +53.2%
Grand Theft Auto V	62 −53.2%	95−100 +53.2%
PLAYERUNKNOWN'S BATTLEGROUNDS	170−180 −60%	280−290 +60%
Red Dead Redemption 2	28 −42.9%	40−45 +42.9%
World of Tanks	210−220 −39.5%	300−310 +39.5%

1440p
Ultra Preset

Battlefield 5	63 −58.7%	100−105 +58.7%
Cyberpunk 2077	13 −38.5%	18−20 +38.5%
Far Cry 5	100−110 −60.4%	170−180 +60.4%
Forza Horizon 4	78 −53.8%	120−130 +53.8%
Forza Horizon 5	47 −59.6%	75−80 +59.6%
Metro Exodus	65 −53.8%	100−105 +53.8%
The Witcher 3: Wild Hunt	55−60 −54.5%	85−90 +54.5%
Valorant	82 −58.5%	130−140 +58.5%

4K
High Preset

Counter-Strike 2	14−16 −60%	24−27 +60%
Dota 2	56 −51.8%	85−90 +51.8%
Grand Theft Auto V	56 −51.8%	85−90 +51.8%
Metro Exodus	21 −42.9%	30−33 +42.9%
PLAYERUNKNOWN'S BATTLEGROUNDS	100−110 −60.4%	170−180 +60.4%
Red Dead Redemption 2	19 −57.9%	30−33 +57.9%
The Witcher 3: Wild Hunt	56 −51.8%	85−90 +51.8%

4K
Ultra Preset

Battlefield 5	31 −45.2%	45−50 +45.2%
Counter-Strike 2	14−16 −60%	24−27 +60%
Cyberpunk 2077	6 −50%	9−10 +50%
Dota 2	94 −59.6%	150−160 +59.6%
Far Cry 5	45−50 −59.6%	75−80 +59.6%
Fortnite	45−50 −55.6%	70−75 +55.6%
Forza Horizon 4	43 −51.2%	65−70 +51.2%
Forza Horizon 5	24 −45.8%	35−40 +45.8%
Valorant	41 −58.5%	65−70 +58.5%

This is how GTX 1660 Ti and RTX 4000 SFF Ada Generation compete in popular games:

RTX 4000 SFF Ada Generation is 55% faster in 1080p
RTX 4000 SFF Ada Generation is 58% faster in 1440p
RTX 4000 SFF Ada Generation is 54% faster in 4K

Pros & cons summary

Performance score	32.42	52.10
Recency	22 February 2019	21 March 2023
Maximum RAM amount	6 GB	20 GB
Chip lithography	12 nm	5 nm
Power consumption (TDP)	120 Watt	70 Watt

RTX 4000 SFF Ada Generation has a 60.7% higher aggregate performance score, an age advantage of 4 years, a 233.3% higher maximum VRAM amount, a 140% more advanced lithography process, and 71.4% lower power consumption.

The RTX 4000 SFF Ada Generation is our recommended choice as it beats the GeForce GTX 1660 Ti in performance tests.

Be aware that GeForce GTX 1660 Ti is a desktop card while RTX 4000 SFF Ada Generation is a workstation one.

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