NVIDIA GeForce RTX 5090 Mobile vs AMD Radeon RX 6650M
We compared two Mobile platform GPUs: 24GB VRAM GeForce RTX 5090 Mobile and 8GB VRAM Radeon RX 6650M to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 5090 Mobile 's Advantages
Released 3 years and 2 months late
More VRAM (24GB vs 8GB)
Larger VRAM bandwidth (896.0GB/s vs 256.0GB/s)
8704 additional rendering cores
Lower TDP (95W vs 120W)
AMD Radeon RX 6650M 's Advantages
Boost Clock has increased by 59% (2416MHz vs 1515MHz)
Score
Benchmark
FP32 (float)
GeForce RTX 5090 Mobile
+267%
31.8 TFLOPS
Radeon RX 6650M
8.659 TFLOPS
Graphics Card
Mar 2025
Release Date
Jan 2022
GeForce 50 Mobile
Generation
Mobility Radeon
Mobile
Type
Mobile
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x8
Clock Speeds
990 MHz
Base Clock
2068 MHz
1515 MHz
Boost Clock
2416 MHz
1750 MHz
Memory Clock
2000 MHz
Memory
24GB
Memory Size
8GB
GDDR7
Memory Type
GDDR6
256bit
Memory Bus
128bit
896.0GB/s
Bandwidth
256.0GB/s
Render Config
-
Compute Units
28
82
SM Count
-
10496
Shading Units
1792
328
TMUs
112
112
ROPs
64
328
Tensor Cores
-
82
RT Cores
28
128 KB (per SM)
L1 Cache
128 KB per Array
64 MB
L2 Cache
2 MB
-
L3 Cache
32 MB
Theoretical Performance
169.7 GPixel/s
Pixel Rate
154.6 GPixel/s
496.9 GTexel/s
Texture Rate
270.6 GTexel/s
31.80 TFLOPS
FP16 (half)
17.32 TFLOPS
31.80 TFLOPS
FP32 (float)
8.659 TFLOPS
496.9 GFLOPS
FP64 (double)
541.2 GFLOPS
Board Design
95W
TDP
120W
550 W
Suggested PSU
-
Portable Device Dependent
Outputs
No outputs
None
Power Connectors
None
Graphics Processor
GB203
GPU Name
Navi 23
GN22-X11-A1
GPU Variant
-
Blackwell 2.0
Architecture
RDNA 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
7 nm
45.6 billion
Transistors
11.06 billion
378 mm²
Die Size
237 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.4
Vulkan
1.3
12.0
CUDA
-
6.8
Shader Model
6.5
