AMD Radeon AI PRO R9700 vs NVIDIA GeForce RTX 5090 D
We compared two Desktop platform GPUs: 32GB VRAM Radeon AI PRO R9700 and 32GB VRAM GeForce RTX 5090 D to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon AI PRO R9700 's Advantages
Released 6 months late
Boost Clock has increased by 21% (2920MHz vs 2407MHz)
Lower TDP (300W vs 575W)
NVIDIA GeForce RTX 5090 D 's Advantages
Larger VRAM bandwidth (1.79TB/s vs 644.6GB/s)
17664 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon AI PRO R9700
47.84 TFLOPS
GeForce RTX 5090 D
+119%
104.8 TFLOPS
Graphics Card
Jul 2025
Release Date
Jan 2025
Radeon Pro Navi
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1660 MHz
Base Clock
2017 MHz
2920 MHz
Boost Clock
2407 MHz
2518 MHz
Memory Clock
1750 MHz
Memory
32GB
Memory Size
32GB
GDDR6
Memory Type
GDDR7
256bit
Memory Bus
512bit
644.6GB/s
Bandwidth
1.79TB/s
Render Config
64
Compute Units
-
-
SM Count
170
4096
Shading Units
21760
256
TMUs
680
128
ROPs
176
128
Tensor Cores
680
64
RT Cores
170
-
L1 Cache
128 KB (per SM)
8 MB
L2 Cache
96 MB
64 MB
L3 Cache
-
Theoretical Performance
373.8 GPixel/s
Pixel Rate
423.6 GPixel/s
747.5 GTexel/s
Texture Rate
1637 GTexel/s
95.68 TFLOPS
FP16 (half)
104.8 TFLOPS
47.84 TFLOPS
FP32 (float)
104.8 TFLOPS
1495 GFLOPS
FP64 (double)
1.637 TFLOPS
Board Design
300W
TDP
575W
700 W
Suggested PSU
950 W
4x DisplayPort 2.1a
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1b
1x 16-pin
Power Connectors
1x 16-pin
Graphics Processor
Navi 48
GPU Name
GB202
Navi 48 XTW
GPU Variant
-
RDNA 4.0
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
4 nm
Process Size
5 nm
53.9 billion
Transistors
92.2 billion
357 mm²
Die Size
750 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.2
OpenCL
3.0
1.3
Vulkan
1.4
-
CUDA
10.1
6.8
Shader Model
6.8
