Radeon Pro Vega 48 and GeForce RTX 4070 Ti - video card comparison
Passmark - benchmark score Radeon Pro Vega 48 vs GeForce RTX 4070 Ti
Radeon Pro Vega 48
11638
GeForce RTX 4070 Ti
32719
Radeon Pro Vega 48
GeForce RTX 4070 Ti
Architecture
GCN 5.0 (2017−2020)
Ada Lovelace
GPU code name
Vega 10
AD104-400
Market segment
Mobile workstation
Desktop
Release date
March 2019
January 2023
Interface
PCIe 3.0 x16
PCIe 4.0 x16
Supplementary power connectors
None
1x 12-pin
Boost clock speed
1300 MHz
2610 MHz
Core clock speed
1200 MHz
2310 MHz
Manufacturing process technology
14 nm
5 nm
Number of transistors
12,500 million
35,800 million
Pipelines / CUDA cores
3072
7680
Power consumption (TDP)
-
285 Watt
Texture fill rate
249.6
626.4
Memory type
HBM2
GDDR6X
Maximum RAM amount
8 GB
12 GB
Memory bus width
2048 Bit
192 Bit
Memory clock speed
1572 MHz
21000 MHz
Memory bandwidth
402.4 GB/s
504.2 GB/s
Shared memory
-
-
Display Connectors
No outputs
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
-
+
DirectX
12 (12_1)
12 Ultimate (12_2)
CUDA
-
8.9
OpenCL
2.0
3.0
OpenGL
4.6
4.6
Shader Model
6.4
6.7
Vulkan
1.1.125
1.3