GeForce RTX 5090 vs Radeon Vega Frontier Edition Watercooled
We compared two Desktop platform GPUs: 32GB VRAM GeForce RTX 5090 and 16GB VRAM Radeon Vega Frontier Edition Watercooled to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 5090 Advantages
Released 7 years and 6 months late
Boost Clock has increased by 50% (2407MHz vs 1600MHz)
More VRAM (32GB vs 16GB)
Larger VRAM bandwidth (1.79TB/s vs 483.8GB/s)
17664 additional rendering cores
Radeon Vega Frontier Edition Watercooled Advantages
Lower TDP (375W vs 575W)
Score
Benchmark
FP32 (float)
GeForce RTX 5090
+699%
104800
Radeon Vega Frontier Edition Watercooled
13110
Graphics Card
Jan 2025
Release Date
Jul 2017
GeForce 50
Generation
Radeon Pro
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
2017 MHz
Base Clock
1382 MHz
2407 MHz
Boost Clock
1600 MHz
1750 MHz
Memory Clock
945 MHz
Memory
32GB
Memory Size
16GB
GDDR7
Memory Type
HBM2
512bit
Memory Bus
2048bit
1.79TB/s
Bandwidth
483.8GB/s
Render Config
-
Compute Units
64
170
SM Count
-
21760
Shading Units
4096
680
TMUs
256
176
ROPs
64
680
Tensor Cores
-
170
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
96 MB
L2 Cache
4 MB
Theoretical Performance
423.6 GPixel/s
Pixel Rate
102.4 GPixel/s
1637 GTexel/s
Texture Rate
409.6 GTexel/s
104.8 TFLOPS
FP16 (half)
26.21 TFLOPS
104.8 TFLOPS
FP32 (float)
13.11 TFLOPS
1.637 TFLOPS
FP64 (double)
819.2 GFLOPS
Board Design
575W
TDP
375W
950 W
Suggested PSU
750 W
1x HDMI 2.1b
3x DisplayPort 2.1b
3x DisplayPort 2.1b
Outputs
1x HDMI 2.0b
3x DisplayPort 1.4a
3x DisplayPort 1.4a
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
GB202
GPU Name
Vega 10
GB202-300-A1
GPU Variant
Vega 10 XTX LCS
Blackwell 2.0
Architecture
GCN 5.0
TSMC
Foundry
GlobalFoundries
5 nm
Process Size
14 nm
92.2 billion
Transistors
12.5 billion
750 mm²
Die Size
495 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.4
Vulkan
1.2
12.0
CUDA
-
6.8
Shader Model
6.4