NVIDIA GeForce RTX 4070 vs AMD Radeon Pro V620
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 and 32GB VRAM Radeon Pro V620 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4070 's Advantages
Released 1 years and 5 months late
Boost Clock has increased by 12% (2475MHz vs 2200MHz)
1280 additional rendering cores
Lower TDP (200W vs 300W)
AMD Radeon Pro V620 's Advantages
More VRAM (32GB vs 12GB)
Larger VRAM bandwidth (512.0GB/s vs 504.2GB/s)
Score
Benchmark
FP32 (float)
GeForce RTX 4070
+43%
29.15 TFLOPS
Radeon Pro V620
20.28 TFLOPS
Graphics Card
Apr 2023
Release Date
Nov 2021
GeForce 40
Generation
Radeon Pro
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1920 MHz
Base Clock
1825 MHz
2475 MHz
Boost Clock
2200 MHz
1313 MHz
Memory Clock
2000 MHz
Memory
12GB
Memory Size
32GB
GDDR6X
Memory Type
GDDR6
192bit
Memory Bus
256bit
504.2GB/s
Bandwidth
512.0GB/s
Render Config
-
Compute Units
72
46
SM Count
-
5888
Shading Units
4608
184
TMUs
288
64
ROPs
128
184
Tensor Cores
-
46
RT Cores
72
128 KB (per SM)
L1 Cache
128 KB per Array
36 MB
L2 Cache
4 MB
-
L3 Cache
128 MB
Theoretical Performance
158.4 GPixel/s
Pixel Rate
281.6 GPixel/s
455.4 GTexel/s
Texture Rate
633.6 GTexel/s
29.15 TFLOPS
FP16 (half)
40.55 TFLOPS
29.15 TFLOPS
FP32 (float)
20.28 TFLOPS
455.4 GFLOPS
FP64 (double)
1267 GFLOPS
Board Design
200W
TDP
300W
550 W
Suggested PSU
700 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
AD104
GPU Name
Navi 21
AD104-250-A1
GPU Variant
Navi 21 XT
(215-121000177)
Ada Lovelace
Architecture
RDNA 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
7 nm
35.8 billion
Transistors
26.8 billion
295 mm²
Die Size
520 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.3
8.9
CUDA
-
6.7
Shader Model
6.5
