NVIDIA GeForce RTX 4070 SUPER vs AMD Radeon RX 7900 XT

Comparative analysis of NVIDIA GeForce RTX 4070 SUPER and AMD Radeon RX 7900 XT 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 - Ocean Surface Simulation (Frames/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).

 

Differences

Reasons to consider the NVIDIA GeForce RTX 4070 SUPER

  • Videocard is newer: launch date 1 year(s) 2 month(s) later
  • Around 32% higher core clock speed: 1980 MHz vs 1500 MHz
  • Around 3% higher boost clock speed: 2475 MHz vs 2394 MHz
  • Around 33% higher pipelines: 7168 vs 5376
  • Around 36% lower typical power consumption: 220 Watt vs 300 Watt
  • Around 4% better performance in PassMark - G3D Mark: 30014 vs 28786
  • Around 13% better performance in Geekbench - OpenCL: 192204 vs 169684
Specifications (specs)
Launch date 8 Jan 2024 vs 3 Nov 2022
Core clock speed 1980 MHz vs 1500 MHz
Boost clock speed 2475 MHz vs 2394 MHz
Pipelines 7168 vs 5376
Thermal Design Power (TDP) 220 Watt vs 300 Watt
Benchmarks
PassMark - G3D Mark 30014 vs 28786
Geekbench - OpenCL 192204 vs 169684

Reasons to consider the AMD Radeon RX 7900 XT

  • Around 45% higher texture fill rate: 804.4 GTexel/s vs 554.4 GTexel/s
  • Around 67% higher maximum memory size: 20 GB vs 12 GB
  • Around 90% higher memory clock speed: 2500 MHz, 20 Gbps effective vs 1313 MHz, 21 Gbps effective
  • Around 4% better performance in PassMark - G2D Mark: 1191 vs 1150
  • Around 27% better performance in 3DMark Fire Strike - Graphics Score: 26656 vs 21062
Specifications (specs)
Texture fill rate 804.4 GTexel/s vs 554.4 GTexel/s
Maximum memory size 20 GB vs 12 GB
Memory clock speed 2500 MHz, 20 Gbps effective vs 1313 MHz, 21 Gbps effective
Benchmarks
PassMark - G2D Mark 1191 vs 1150
3DMark Fire Strike - Graphics Score 26656 vs 21062

Compare benchmarks

GPU 1: NVIDIA GeForce RTX 4070 SUPER
GPU 2: AMD Radeon RX 7900 XT

PassMark - G2D Mark
GPU 1
GPU 2
1150
1191
PassMark - G3D Mark
GPU 1
GPU 2
30014
28786
Geekbench - OpenCL
GPU 1
GPU 2
192204
169684
3DMark Fire Strike - Graphics Score
GPU 1
GPU 2
21062
26656
Name NVIDIA GeForce RTX 4070 SUPER AMD Radeon RX 7900 XT
PassMark - G2D Mark 1150 1191
PassMark - G3D Mark 30014 28786
Geekbench - OpenCL 192204 169684
3DMark Fire Strike - Graphics Score 21062 26656
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 343.519
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 12483.531
CompuBench 1.5 Desktop - T-Rex (Frames/s) 60.185
CompuBench 1.5 Desktop - Video Composition (Frames/s) 320.733
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 2714.187

Compare specifications (specs)

NVIDIA GeForce RTX 4070 SUPER AMD Radeon RX 7900 XT

Essentials

Architecture Ada Lovelace RDNA 3.0
Code name AD104 Navi 31
Launch date 8 Jan 2024 3 Nov 2022
Place in performance rating 15 19

Technical info

Boost clock speed 2475 MHz 2394 MHz
Core clock speed 1980 MHz 1500 MHz
Manufacturing process technology 5 nm 5 nm
Pipelines 7168 5376
Pixel fill rate 198.0 GPixel/s 459.6 GPixel/s
Texture fill rate 554.4 GTexel/s 804.4 GTexel/s
Thermal Design Power (TDP) 220 Watt 300 Watt
Transistor count 35800 million 57700 million
Compute units 84
Peak Double Precision (FP64) Performance 3.218 TFLOPS (1:16)
Peak Half Precision (FP16) Performance 103.0 TFLOPS (2:1)
Peak Single Precision (FP32) Performance 51.48 TFLOPS

Video outputs and ports

Display Connectors 1x HDMI 2.1, 3x DisplayPort 1.4a 1x HDMI 2.1a, 2x DisplayPort 2.1, 1x USB Type-C

Compatibility, dimensions and requirements

Form factor Dual-slot Dual-slot
Height 42 mm, 1.7 inches 51 mm, 2 inches
Interface PCIe 4.0 x16 PCIe 4.0 x16
Length 267 mm, 10.5 inches 276 mm, 10.9 inches
Recommended system power (PSU) 550 Watt 700 Watt
Supplementary power connectors 1x 16-pin 2x 8-pin
Width 112 mm, 4.4 inches 135 mm, 5.3 inches

API support

DirectX 12 Ultimate (12_2) 12 Ultimate (12_2)
OpenCL 3.0 2.1
OpenGL 4.6 4.6
Shader Model 6.7 6.7
Vulkan

Memory

Maximum RAM amount 12 GB 20 GB
Memory bandwidth 504.2 GB/s 800.0 GB/s
Memory bus width 192 bit 320 bit
Memory clock speed 1313 MHz, 21 Gbps effective 2500 MHz, 20 Gbps effective
Memory type GDDR6X GDDR6