GeForce RTX 3070 and Radeon PRO W7900 - video card comparison
Passmark - benchmark score GeForce RTX 3070 vs Radeon PRO W7900
GeForce RTX 3070
23060
Radeon PRO W7900
30067
GeForce RTX 3070
Radeon PRO W7900
Architecture
Ampere (2020−2022)
RDNA 3.0 (2022)
GPU code name
Ampere GA104
Navi 31
Market segment
Desktop
Workstation
Release date
September 2020
April 2023
Interface
PCIe 4.0 x16
PCIe 4.0 x16
Supplementary power connectors
1x 12-pin
2x 8-pin
Boost clock speed
1725 MHz
2495 MHz
Core clock speed
1500 MHz
-
Manufacturing process technology
8 nm
5 nm
Number of transistors
17,400 million
57,700 million
Pipelines / CUDA cores
5888
6144
Power consumption (TDP)
220 Watt
295 Watt
Texture fill rate
317.4
958.1
Memory type
GDDR6
GDDR6
Maximum RAM amount
8 GB
48 GB
Memory bus width
256 Bit
384 Bit
Memory clock speed
14000 MHz
18 GB/s
Memory bandwidth
448.0 GB/s
864.0 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
3x DisplayPort 2.1, 1x mini-DisplayPort 2.1
HDMI
+
-
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
CUDA
8.5
-
OpenCL
2.0
2.2
OpenGL
4.6
4.6
Shader Model
6.5
6.7
Vulkan
1.2
1.3