GeForce RTX 5070 vs Radeon Pro Vega II Duo
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 5070 and 32GB VRAM Radeon Pro Vega II Duo to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 5070 Advantages
Released 5 years and 9 months late
Boost Clock has increased by 46% (2512MHz vs 1720MHz)
2048 additional rendering cores
Lower TDP (250W vs 475W)
Radeon Pro Vega II Duo Advantages
More VRAM (32GB vs 12GB)
Larger VRAM bandwidth (1020GB/s vs 672.0GB/s)
Score
Benchmark
FP32 (float)
GeForce RTX 5070
+119%
30870
Radeon Pro Vega II Duo
14090
Blender
GeForce RTX 5070
+653%
6182
Radeon Pro Vega II Duo
820
Graphics Card
Mar 2025
Release Date
Jun 2019
GeForce 50
Generation
Radeon Pro Mac
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
Apple MPX
Clock Speeds
2325 MHz
Base Clock
1400 MHz
2512 MHz
Boost Clock
1720 MHz
1750 MHz
Memory Clock
1000 MHz
Memory
12GB
Memory Size
32GB
GDDR7
Memory Type
HBM2
192bit
Memory Bus
4096bit
672.0GB/s
Bandwidth
1020GB/s
Render Config
-
Compute Units
64
48
SM Count
-
6144
Shading Units
4096
192
TMUs
256
80
ROPs
64
192
Tensor Cores
-
48
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
48 MB
L2 Cache
4 MB
Theoretical Performance
201.0 GPixel/s
Pixel Rate
110.1 GPixel/s
482.3 GTexel/s
Texture Rate
440.3 GTexel/s
30.87 TFLOPS
FP16 (half)
28.18 TFLOPS
30.87 TFLOPS
FP32 (float)
14.09 TFLOPS
482.3 GFLOPS
FP64 (double)
7.045 TFLOPS
Board Design
250W
TDP
475W
600 W
Suggested PSU
850 W
1x HDMI 2.1b
3x DisplayPort 2.1b
3x DisplayPort 2.1b
Outputs
1x HDMI 2.0b
4x Thunderbolt
4x Thunderbolt
1x 16-pin
Power Connectors
None
Graphics Processor
GB205
GPU Name
Vega 20
GB205-300-A1
GPU Variant
Vega 20 XT
Blackwell 2.0
Architecture
GCN 5.1
TSMC
Foundry
TSMC
5 nm
Process Size
7 nm
31.1 billion
Transistors
13.23 billion
263 mm²
Die Size
331 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.4
Vulkan
1.3
10.1
CUDA
-
6.8
Shader Model
6.7