NVIDIA GeForce RTX 4070 vs NVIDIA GeForce GTX 1660 SUPER

Comparative analysis of NVIDIA GeForce RTX 4070 and NVIDIA GeForce GTX 1660 SUPER videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: PassMark - G2D Mark, PassMark - G3D Mark, Geekbench - OpenCL, 3DMark Fire Strike - Graphics Score, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps).

NVIDIA GeForce RTX 4070

NVIDIA GeForce GTX 1660 SUPER

Differences

Reasons to consider the NVIDIA GeForce RTX 4070

Videocard is newer: launch date 5 year(s) 10 month(s) later
Around 51% higher core clock speed: 2310 MHz vs 1530 MHz
Around 46% higher boost clock speed: 2610 MHz vs 1785 MHz
3.1x more texture fill rate: 480.2 GTexel/s vs 157.1 GTexel/s
4.2x more pipelines: 5888 vs 1408
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 4 nm vs 12 nm
2x more maximum memory size: 12 GB vs 6 GB
Around 45% better performance in PassMark - G2D Mark: 1166 vs 804
2.1x better performance in PassMark - G3D Mark: 26959 vs 12712
2.7x better performance in Geekbench - OpenCL: 168049 vs 62641
3x better performance in 3DMark Fire Strike - Graphics Score: 3854 vs 1278
2.2x better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 417.133 vs 187.131
3.5x better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 55.476 vs 15.882
2.1x better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 245.639 vs 117.673
2.7x better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 2459.317 vs 901.388

Specifications (specs)
Launch date	2023 vs 29 Oct 2019
Core clock speed	2310 MHz vs 1530 MHz
Boost clock speed	2610 MHz vs 1785 MHz
Texture fill rate	480.2 GTexel/s vs 157.1 GTexel/s
Pipelines	5888 vs 1408
Manufacturing process technology	4 nm vs 12 nm
Maximum memory size	12 GB vs 6 GB
Benchmarks
PassMark - G2D Mark	1166 vs 804
PassMark - G3D Mark	26959 vs 12712
Geekbench - OpenCL	168049 vs 62641
3DMark Fire Strike - Graphics Score	3854 vs 1278
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	417.133 vs 187.131
CompuBench 1.5 Desktop - T-Rex (Frames/s)	55.476 vs 15.882
CompuBench 1.5 Desktop - Video Composition (Frames/s)	245.639 vs 117.673
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	2459.317 vs 901.388

Reasons to consider the NVIDIA GeForce GTX 1660 SUPER

2.3x lower typical power consumption: 125 Watt vs 285 Watt

Thermal Design Power (TDP)	125 Watt vs 285 Watt

Compare benchmarks

GPU 1: NVIDIA GeForce RTX 4070
GPU 2: NVIDIA GeForce GTX 1660 SUPER

PassMark - G2D Mark

GPU 1

GPU 2

1166

804

PassMark - G3D Mark

GPU 1

GPU 2

26959

12712

Geekbench - OpenCL

GPU 1

GPU 2

168049

62641

3DMark Fire Strike - Graphics Score

GPU 1

GPU 2

3854

1278

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

417.133

187.131

CompuBench 1.5 Desktop - T-Rex (Frames/s)

GPU 1

GPU 2

55.476

15.882

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

245.639

117.673

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

2459.317

901.388

Name	NVIDIA GeForce RTX 4070	NVIDIA GeForce GTX 1660 SUPER
PassMark - G2D Mark	1166	804
PassMark - G3D Mark	26959	12712
Geekbench - OpenCL	168049	62641
3DMark Fire Strike - Graphics Score	3854	1278
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	417.133	187.131
CompuBench 1.5 Desktop - T-Rex (Frames/s)	55.476	15.882
CompuBench 1.5 Desktop - Video Composition (Frames/s)	245.639	117.673
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	2459.317	901.388
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		2548.187
GFXBench 4.0 - Car Chase Offscreen (Frames)		17812
GFXBench 4.0 - Manhattan (Frames)		3717
GFXBench 4.0 - T-Rex (Frames)		3351
GFXBench 4.0 - Car Chase Offscreen (Fps)		17812
GFXBench 4.0 - Manhattan (Fps)		3717
GFXBench 4.0 - T-Rex (Fps)		3351

Compare specifications (specs)

	NVIDIA GeForce RTX 4070	NVIDIA GeForce GTX 1660 SUPER
Essentials
Architecture	Ada Lovelace	Turing
Code name	AD104	TU116
Launch date	2023	29 Oct 2019
Place in performance rating	35	223
Launch price (MSRP)		$229
Type		Desktop
Technical info
Boost clock speed	2610 MHz	1785 MHz
Core clock speed	2310 MHz	1530 MHz
Manufacturing process technology	4 nm	12 nm
Peak Double Precision (FP64) Performance	480.2 GFLOPS (1:64)	157.1 GFLOPS (1:32)
Peak Half Precision (FP16) Performance	30.74 TFLOPS (1:1)	10.05 TFLOPS (2:1)
Peak Single Precision (FP32) Performance	30.74 TFLOPS	5.027 TFLOPS
Pipelines	5888	1408
Pixel fill rate	167.0 GPixel/s	85.68 GPixel/s
Texture fill rate	480.2 GTexel/s	157.1 GTexel/s
Thermal Design Power (TDP)	285 Watt	125 Watt
Transistor count	35800 million	6600 million
Video outputs and ports
Display Connectors	1x HDMI 2.1, 3x DisplayPort 1.4a	1x DVI, 1x HDMI, 1x DisplayPort
Compatibility, dimensions and requirements
Form factor	Dual-slot
Height	61 mm, 2.4 inches
Interface	PCIe 4.0 x16	PCIe 3.0 x16
Length	336 mm, 13.2 inches	9 inches (229 mm)
Recommended system power (PSU)	600 Watt	350 Watt
Supplementary power connectors	1x 12-pin	1x 8-pin
Width	140 mm, 5.5 inches	Dual-slot
API support
DirectX	12 Ultimate (12_2)	12.1
OpenCL	3.0	1.2
OpenGL	4.6	4.6
Shader Model	6.7	6.4
Vulkan
Memory
Maximum RAM amount	12 GB	6 GB
Memory bandwidth	504.2 GB/s	336.0 GB/s
Memory bus width	192 bit	192 bit
Memory clock speed	1313 MHz, 21 Gbps effective
Memory type	GDDR6X	GDDR6