NVIDIA GeForce RTX 4070 vs NVIDIA GeForce RTX 3080 Ti

Comparative analysis of NVIDIA GeForce RTX 4070 and NVIDIA GeForce RTX 3080 Ti 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 RTX 3080 Ti

Differences

Reasons to consider the NVIDIA GeForce RTX 4070

Videocard is newer: launch date 4 year(s) 3 month(s) later
Around 69% higher core clock speed: 2310 MHz vs 1365 MHz
Around 57% higher boost clock speed: 2610 MHz vs 1665 MHz
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 4 nm vs 8 nm
Around 23% lower typical power consumption: 285 Watt vs 350 Watt
Around 11% higher memory clock speed: 1313 MHz, 21 Gbps effective vs 1188 MHz, 19 Gbps effective
Around 7% better performance in PassMark - G2D Mark: 1166 vs 1088
Around 90% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 245.639 vs 129.036
Around 1% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 2459.317 vs 2441.001

Specifications (specs)
Launch date	2023 vs 31 May 2021
Core clock speed	2310 MHz vs 1365 MHz
Boost clock speed	2610 MHz vs 1665 MHz
Manufacturing process technology	4 nm vs 8 nm
Thermal Design Power (TDP)	285 Watt vs 350 Watt
Memory clock speed	1313 MHz, 21 Gbps effective vs 1188 MHz, 19 Gbps effective
Benchmarks
PassMark - G2D Mark	1166 vs 1088
PassMark - G3D Mark	26959 vs 26935
CompuBench 1.5 Desktop - Video Composition (Frames/s)	245.639 vs 129.036
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	2459.317 vs 2441.001

Reasons to consider the NVIDIA GeForce RTX 3080 Ti

Around 11% higher texture fill rate: 532.8 GTexel/s vs 480.2 GTexel/s
Around 74% higher pipelines: 10240 vs 5888
Around 24% better performance in Geekbench - OpenCL: 209081 vs 168049
Around 32% better performance in 3DMark Fire Strike - Graphics Score: 5077 vs 3854
Around 16% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 485.179 vs 417.133
Around 9% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 60.472 vs 55.476

Specifications (specs)
Texture fill rate	532.8 GTexel/s vs 480.2 GTexel/s
Pipelines	10240 vs 5888
Benchmarks
Geekbench - OpenCL	209081 vs 168049
3DMark Fire Strike - Graphics Score	5077 vs 3854
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	485.179 vs 417.133
CompuBench 1.5 Desktop - T-Rex (Frames/s)	60.472 vs 55.476

Compare benchmarks

GPU 1: NVIDIA GeForce RTX 4070
GPU 2: NVIDIA GeForce RTX 3080 Ti

PassMark - G2D Mark

GPU 1

GPU 2

1166

1088

PassMark - G3D Mark

GPU 1

GPU 2

26959

26935

Geekbench - OpenCL

GPU 1

GPU 2

168049

209081

3DMark Fire Strike - Graphics Score

GPU 1

GPU 2

3854

5077

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

417.133

485.179

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

GPU 1

GPU 2

55.476

60.472

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

245.639

129.036

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

2459.317

2441.001

Name	NVIDIA GeForce RTX 4070	NVIDIA GeForce RTX 3080 Ti
PassMark - G2D Mark	1166	1088
PassMark - G3D Mark	26959	26935
Geekbench - OpenCL	168049	209081
3DMark Fire Strike - Graphics Score	3854	5077
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	417.133	485.179
CompuBench 1.5 Desktop - T-Rex (Frames/s)	55.476	60.472
CompuBench 1.5 Desktop - Video Composition (Frames/s)	245.639	129.036
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	2459.317	2441.001
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		661.977
GFXBench 4.0 - Car Chase Offscreen (Frames)		34770
GFXBench 4.0 - Manhattan (Frames)		3718
GFXBench 4.0 - T-Rex (Frames)		3359
GFXBench 4.0 - Car Chase Offscreen (Fps)		34770
GFXBench 4.0 - Manhattan (Fps)		3718
GFXBench 4.0 - T-Rex (Fps)		3359

Compare specifications (specs)

	NVIDIA GeForce RTX 4070	NVIDIA GeForce RTX 3080 Ti
Essentials
Architecture	Ada Lovelace	Ampere
Code name	AD104	GA102
Launch date	2023	31 May 2021
Place in performance rating	35	60
Launch price (MSRP)		$1199
Type		Desktop
Technical info
Boost clock speed	2610 MHz	1665 MHz
Core clock speed	2310 MHz	1365 MHz
Manufacturing process technology	4 nm	8 nm
Peak Double Precision (FP64) Performance	480.2 GFLOPS (1:64)	532.8 GFLOPS (1:64)
Peak Half Precision (FP16) Performance	30.74 TFLOPS (1:1)	34.10 TFLOPS (1:1)
Peak Single Precision (FP32) Performance	30.74 TFLOPS	34.10 TFLOPS
Pipelines	5888	10240
Pixel fill rate	167.0 GPixel/s	186.5 GPixel/s
Texture fill rate	480.2 GTexel/s	532.8 GTexel/s
Thermal Design Power (TDP)	285 Watt	350 Watt
Transistor count	35800 million	28300 million
Video outputs and ports
Display Connectors	1x HDMI 2.1, 3x DisplayPort 1.4a	1x HDMI 2.1, 3x DisplayPort 1.4a
Compatibility, dimensions and requirements
Form factor	Dual-slot	Dual-slot
Height	61 mm, 2.4 inches	40 mm, 1.6 inches
Interface	PCIe 4.0 x16	PCIe 4.0 x16
Length	336 mm, 13.2 inches	285 mm, 11.2 inches
Recommended system power (PSU)	600 Watt	750 Watt
Supplementary power connectors	1x 12-pin	1x 12-pin
Width	140 mm, 5.5 inches	112 mm, 4.4 inches
API support
DirectX	12 Ultimate (12_2)	12 Ultimate (12_2)
OpenCL	3.0	3.0
OpenGL	4.6	4.6
Shader Model	6.7	6.7
Vulkan
Memory
Maximum RAM amount	12 GB	12 GB
Memory bandwidth	504.2 GB/s	912.4 GB/s
Memory bus width	192 bit	384 bit
Memory clock speed	1313 MHz, 21 Gbps effective	1188 MHz, 19 Gbps effective
Memory type	GDDR6X	GDDR6X