AMD Radeon RX 6900 XT vs NVIDIA GeForce RTX 3070

Comparative analysis of AMD Radeon RX 6900 XT and NVIDIA GeForce RTX 3070 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 - 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 AMD Radeon RX 6900 XT

  • Videocard is newer: launch date 1 month(s) later
  • Around 22% higher core clock speed: 1825 MHz vs 1500 MHz
  • Around 30% higher boost clock speed: 2250 MHz vs 1725 MHz
  • 2.3x more texture fill rate: 720.0 GTexel/s vs 317.4 GTexel/s
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 7 nm vs 8 nm
  • 2x more maximum memory size: 16 GB vs 8 GB
  • Around 14% higher memory clock speed: 2000 MHz (16 Gbps effective) vs 1750 MHz (14 Gbps effective)
  • Around 20% better performance in PassMark - G3D Mark: 26259 vs 21816
  • Around 18% better performance in PassMark - G2D Mark: 1135 vs 965
  • Around 22% better performance in Geekbench - OpenCL: 165115 vs 135018
  • Around 17% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 532.345 vs 455.06
  • Around 24% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 50.602 vs 40.794
  • Around 33% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 288.807 vs 216.709
  • Around 58% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 2563.25 vs 1619.54
  • Around 40% better performance in 3DMark Fire Strike - Graphics Score: 19167 vs 13722
Specifications (specs)
Launch date 28 Oct 2020 vs 1 Sep 2020
Core clock speed 1825 MHz vs 1500 MHz
Boost clock speed 2250 MHz vs 1725 MHz
Texture fill rate 720.0 GTexel/s vs 317.4 GTexel/s
Manufacturing process technology 7 nm vs 8 nm
Maximum memory size 16 GB vs 8 GB
Memory clock speed 2000 MHz (16 Gbps effective) vs 1750 MHz (14 Gbps effective)
Benchmarks
PassMark - G3D Mark 26259 vs 21816
PassMark - G2D Mark 1135 vs 965
Geekbench - OpenCL 165115 vs 135018
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 532.345 vs 455.06
CompuBench 1.5 Desktop - T-Rex (Frames/s) 50.602 vs 40.794
CompuBench 1.5 Desktop - Video Composition (Frames/s) 288.807 vs 216.709
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 2563.25 vs 1619.54
3DMark Fire Strike - Graphics Score 19167 vs 13722

Reasons to consider the NVIDIA GeForce RTX 3070

  • Around 15% higher pipelines: 5888 vs 5120
  • Around 36% lower typical power consumption: 220 Watt vs 300 Watt
  • Around 90% better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 30988 vs 16267
  • Around 66% better performance in GFXBench 4.0 - Manhattan (Frames): 6191 vs 3726
  • Around 66% better performance in GFXBench 4.0 - T-Rex (Frames): 5592 vs 3378
  • Around 90% better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 30988 vs 16267
  • Around 66% better performance in GFXBench 4.0 - Manhattan (Fps): 6191 vs 3726
  • Around 66% better performance in GFXBench 4.0 - T-Rex (Fps): 5592 vs 3378
Specifications (specs)
Pipelines 5888 vs 5120
Thermal Design Power (TDP) 220 Watt vs 300 Watt
Benchmarks
GFXBench 4.0 - Car Chase Offscreen (Frames) 30988 vs 16267
GFXBench 4.0 - Manhattan (Frames) 6191 vs 3726
GFXBench 4.0 - T-Rex (Frames) 5592 vs 3378
GFXBench 4.0 - Car Chase Offscreen (Fps) 30988 vs 16267
GFXBench 4.0 - Manhattan (Fps) 6191 vs 3726
GFXBench 4.0 - T-Rex (Fps) 5592 vs 3378

Compare benchmarks

GPU 1: AMD Radeon RX 6900 XT
GPU 2: NVIDIA GeForce RTX 3070

PassMark - G3D Mark
GPU 1
GPU 2
26259
21816
PassMark - G2D Mark
GPU 1
GPU 2
1135
965
Geekbench - OpenCL
GPU 1
GPU 2
165115
135018
CompuBench 1.5 Desktop - Face Detection (mPixels/s)
GPU 1
GPU 2
532.345
455.06
CompuBench 1.5 Desktop - T-Rex (Frames/s)
GPU 1
GPU 2
50.602
40.794
CompuBench 1.5 Desktop - Video Composition (Frames/s)
GPU 1
GPU 2
288.807
216.709
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)
GPU 1
GPU 2
2563.25
1619.54
GFXBench 4.0 - Car Chase Offscreen (Frames)
GPU 1
GPU 2
16267
30988
GFXBench 4.0 - Manhattan (Frames)
GPU 1
GPU 2
3726
6191
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
3378
5592
GFXBench 4.0 - Car Chase Offscreen (Fps)
GPU 1
GPU 2
16267
30988
GFXBench 4.0 - Manhattan (Fps)
GPU 1
GPU 2
3726
6191
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
3378
5592
3DMark Fire Strike - Graphics Score
GPU 1
GPU 2
19167
13722
Name AMD Radeon RX 6900 XT NVIDIA GeForce RTX 3070
PassMark - G3D Mark 26259 21816
PassMark - G2D Mark 1135 965
Geekbench - OpenCL 165115 135018
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 532.345 455.06
CompuBench 1.5 Desktop - T-Rex (Frames/s) 50.602 40.794
CompuBench 1.5 Desktop - Video Composition (Frames/s) 288.807 216.709
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 2563.25 1619.54
GFXBench 4.0 - Car Chase Offscreen (Frames) 16267 30988
GFXBench 4.0 - Manhattan (Frames) 3726 6191
GFXBench 4.0 - T-Rex (Frames) 3378 5592
GFXBench 4.0 - Car Chase Offscreen (Fps) 16267 30988
GFXBench 4.0 - Manhattan (Fps) 3726 6191
GFXBench 4.0 - T-Rex (Fps) 3378 5592
3DMark Fire Strike - Graphics Score 19167 13722
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 5792.308

Compare specifications (specs)

AMD Radeon RX 6900 XT NVIDIA GeForce RTX 3070

Essentials

Architecture RDNA 2.0 Ampere
Code name Navi 21 GA104
Launch date 28 Oct 2020 1 Sep 2020
Launch price (MSRP) $999 $499
Place in performance rating 12 14
Type Desktop Desktop

Technical info

Boost clock speed 2250 MHz 1725 MHz
Compute units 80
Core clock speed 1825 MHz 1500 MHz
Manufacturing process technology 7 nm 8 nm
Peak Double Precision (FP64) Performance 1440 GFLOPS (1:16) 317.4 GFLOPS (1:64)
Peak Half Precision (FP16) Performance 46.08 TFLOPS (2:1) 20.31 TFLOPS (1:1)
Peak Single Precision (FP32) Performance 23.04 TFLOPS 20.31 TFLOPS
Pipelines 5120 5888
Pixel fill rate 288.0 GPixel/s 165.6 GPixel/s
Texture fill rate 720.0 GTexel/s 317.4 GTexel/s
Thermal Design Power (TDP) 300 Watt 220 Watt
Transistor count 26800 million 17400 million

Video outputs and ports

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

Compatibility, dimensions and requirements

Form factor Triple-slot
Height 50 mm (2 inches) 112 mm (4.4 inches)
Interface PCIe 4.0 x16 PCIe 4.0 x16
Length 267 mm (10.5 inches) 242 mm (9.5 inches)
Recommended system power (PSU) 700 Watt 550 Watt
Supplementary power connectors 2x 8-pin 1x 12-pin
Width 120 mm (4.7 inches) Dual-slot

API support

DirectX 12.2 12.1
OpenCL 2.1 2.0
OpenGL 4.6 4.6
Shader Model 6.5 6.5
Vulkan

Memory

Maximum RAM amount 16 GB 8 GB
Memory bandwidth 512 GB/s 448.0 GB/s
Memory bus width 256 bit 256 bit
Memory clock speed 2000 MHz (16 Gbps effective) 1750 MHz (14 Gbps effective)
Memory type GDDR6 GDDR6