NVIDIA GeForce RTX 3070 Ti vs NVIDIA GeForce RTX 2070 Super

Comparative analysis of NVIDIA GeForce RTX 3070 Ti and NVIDIA GeForce RTX 2070 Super videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: PassMark - G3D Mark, PassMark - G2D Mark, Geekbench - OpenCL, 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), 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), 3DMark Fire Strike - Graphics Score, CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s).

 

Differences

Reasons to consider the NVIDIA GeForce RTX 3070 Ti

  • Videocard is newer: launch date 1 year(s) 10 month(s) later
  • 2.4x more pipelines: 6144 vs 2560
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 8 nm vs 12 nm
  • Around 29% better performance in PassMark - G3D Mark: 23411 vs 18198
  • Around 20% better performance in PassMark - G2D Mark: 1051 vs 879
  • Around 40% better performance in Geekbench - OpenCL: 137664 vs 98281
  • Around 17% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 342.287 vs 293.508
  • Around 45% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 42.369 vs 29.145
  • Around 26% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 1807.647 vs 1438.826
  • Around 25% better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 31420 vs 25232
  • 2.4x better performance in GFXBench 4.0 - Manhattan (Frames): 8897 vs 3718
  • 2.4x better performance in GFXBench 4.0 - T-Rex (Frames): 8004 vs 3359
  • Around 25% better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 31420 vs 25232
  • 2.4x better performance in GFXBench 4.0 - Manhattan (Fps): 8897 vs 3718
  • 2.4x better performance in GFXBench 4.0 - T-Rex (Fps): 8004 vs 3359
  • 496.9x better performance in 3DMark Fire Strike - Graphics Score: 3478 vs 7
Specifications (specs)
Launch date 31 May 2021 vs 2 July 2019
Pipelines 6144 vs 2560
Manufacturing process technology 8 nm vs 12 nm
Benchmarks
PassMark - G3D Mark 23411 vs 18198
PassMark - G2D Mark 1051 vs 879
Geekbench - OpenCL 137664 vs 98281
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 342.287 vs 293.508
CompuBench 1.5 Desktop - T-Rex (Frames/s) 42.369 vs 29.145
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 1807.647 vs 1438.826
GFXBench 4.0 - Car Chase Offscreen (Frames) 31420 vs 25232
GFXBench 4.0 - Manhattan (Frames) 8897 vs 3718
GFXBench 4.0 - T-Rex (Frames) 8004 vs 3359
GFXBench 4.0 - Car Chase Offscreen (Fps) 31420 vs 25232
GFXBench 4.0 - Manhattan (Fps) 8897 vs 3718
GFXBench 4.0 - T-Rex (Fps) 8004 vs 3359
3DMark Fire Strike - Graphics Score 3478 vs 7

Reasons to consider the NVIDIA GeForce RTX 2070 Super

  • Around 2% higher core clock speed: 1605 MHz vs 1575 MHz
  • Around 35% lower typical power consumption: 215 Watt vs 290 Watt
  • 11.8x more memory clock speed: 14000 MHz vs 1188 MHz, 19 Gbps effective
  • Around 8% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 158.103 vs 146.214
Specifications (specs)
Core clock speed 1605 MHz vs 1575 MHz
Thermal Design Power (TDP) 215 Watt vs 290 Watt
Memory clock speed 14000 MHz vs 1188 MHz, 19 Gbps effective
Benchmarks
CompuBench 1.5 Desktop - Video Composition (Frames/s) 158.103 vs 146.214

Compare benchmarks

GPU 1: NVIDIA GeForce RTX 3070 Ti
GPU 2: NVIDIA GeForce RTX 2070 Super

PassMark - G3D Mark
GPU 1
GPU 2
23411
18198
PassMark - G2D Mark
GPU 1
GPU 2
1051
879
Geekbench - OpenCL
GPU 1
GPU 2
137664
98281
CompuBench 1.5 Desktop - Face Detection (mPixels/s)
GPU 1
GPU 2
342.287
293.508
CompuBench 1.5 Desktop - T-Rex (Frames/s)
GPU 1
GPU 2
42.369
29.145
CompuBench 1.5 Desktop - Video Composition (Frames/s)
GPU 1
GPU 2
146.214
158.103
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)
GPU 1
GPU 2
1807.647
1438.826
GFXBench 4.0 - Car Chase Offscreen (Frames)
GPU 1
GPU 2
31420
25232
GFXBench 4.0 - Manhattan (Frames)
GPU 1
GPU 2
8897
3718
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
8004
3359
GFXBench 4.0 - Car Chase Offscreen (Fps)
GPU 1
GPU 2
31420
25232
GFXBench 4.0 - Manhattan (Fps)
GPU 1
GPU 2
8897
3718
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
8004
3359
3DMark Fire Strike - Graphics Score
GPU 1
GPU 2
3478
7
Name NVIDIA GeForce RTX 3070 Ti NVIDIA GeForce RTX 2070 Super
PassMark - G3D Mark 23411 18198
PassMark - G2D Mark 1051 879
Geekbench - OpenCL 137664 98281
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 342.287 293.508
CompuBench 1.5 Desktop - T-Rex (Frames/s) 42.369 29.145
CompuBench 1.5 Desktop - Video Composition (Frames/s) 146.214 158.103
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 1807.647 1438.826
GFXBench 4.0 - Car Chase Offscreen (Frames) 31420 25232
GFXBench 4.0 - Manhattan (Frames) 8897 3718
GFXBench 4.0 - T-Rex (Frames) 8004 3359
GFXBench 4.0 - Car Chase Offscreen (Fps) 31420 25232
GFXBench 4.0 - Manhattan (Fps) 8897 3718
GFXBench 4.0 - T-Rex (Fps) 8004 3359
3DMark Fire Strike - Graphics Score 3478 7
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 4045.784

Compare specifications (specs)

NVIDIA GeForce RTX 3070 Ti NVIDIA GeForce RTX 2070 Super

Essentials

Architecture Ampere Turing
Code name GA104 TU104
Launch date 31 May 2021 2 July 2019
Launch price (MSRP) $599 $499
Place in performance rating 66 129
Type Desktop Desktop

Technical info

Boost clock speed 1770 MHz 1770 MHz
Core clock speed 1575 MHz 1605 MHz
Manufacturing process technology 8 nm 12 nm
Peak Double Precision (FP64) Performance 339.8 GFLOPS (1:64)
Peak Half Precision (FP16) Performance 21.75 TFLOPS (1:1)
Peak Single Precision (FP32) Performance 21.75 TFLOPS
Pipelines 6144 2560
Pixel fill rate 169.9 GPixel/s
Texture fill rate 339.8 GTexel/s
Thermal Design Power (TDP) 290 Watt 215 Watt
Transistor count 17400 million 13.6 B
CUDA cores 2560
Maximum GPU temperature 88 C
Render output units 64

Video outputs and ports

Display Connectors 1x HDMI 2.1, 3x DisplayPort 1.4a
Display Port 1.4
DisplayPort support
Dual-link DVI support
G-SYNC support
HDCP
HDMI
Multi monitor support
Number of simultaneous displays 4

Compatibility, dimensions and requirements

Form factor Dual-slot
Interface PCIe 4.0 x16
Length 267 mm, 10.5 inches 10.5” (266.74mm)
Recommended system power (PSU) 600 Watt 650 Watt
Supplementary power connectors 1x 12-pin 6 pin + 8 pin
Width 112 mm, 4.4 inches 2-Slot
Height 4.556” (115.7mm)

API support

DirectX 12 Ultimate (12_2) 12.1
OpenCL 3.0
OpenGL 4.6 4.5
Shader Model 6.7 6.4
Vulkan

Memory

Maximum RAM amount 8 GB 8 GB
Memory bandwidth 608.3 GB/s 448 GB/s
Memory bus width 256 bit 256 bit
Memory clock speed 1188 MHz, 19 Gbps effective 14000 MHz
Memory type GDDR6X GDDR6

Technologies

Ansel
HDMI 2.0b
SLI
VR Ready