GeForce MX250 vs GeForce RTX 4090 Mobile
We compared two Mobile platform GPUs: 2GB VRAM GeForce MX250 and 16GB VRAM GeForce RTX 4090 Mobile to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce MX250 's Advantages
Lower TDP (10W vs 120W)
GeForce RTX 4090 Mobile 's Advantages
Boost Clock has increased by 63% (1695MHz vs 1038MHz)
More VRAM (16GB vs 2GB)
Larger VRAM bandwidth (576.0GB/s vs 48.06GB/s)
9344 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce MX250
797
GeForce RTX 4090 Mobile
+4038%
32980
3DMark Time Spy
GeForce MX250
1079
GeForce RTX 4090 Mobile
+1892%
21498
3DMark Time Spy Extreme
GeForce MX250
222
GeForce RTX 4090 Mobile
+4642%
10528
Blender
GeForce MX250
72
GeForce RTX 4090 Mobile
+10583%
7692
OctaneBench
GeForce MX250
22
GeForce RTX 4090 Mobile
+3145%
714
Graphics Card
Unknown
Release Date
Jan 2023
GeForce MX
Generation
GeForce 40 Mobile
Mobile
Type
Mobile
PCIe 3.0 x4
Bus Interface
PCIe 4.0 x16
Clock Speeds
937 MHz
Base Clock
1335 MHz
1038 MHz
Boost Clock
1695 MHz
1502 MHz
Memory Clock
2250 MHz
Memory
2GB
Memory Size
16GB
GDDR5
Memory Type
GDDR6
64bit
Memory Bus
256bit
48.06GB/s
Bandwidth
576.0GB/s
Render Config
3
SM Count
76
384
Shading Units
9728
24
TMUs
304
16
ROPs
112
-
Tensor Cores
304
-
RT Cores
76
48 KB (per SM)
L1 Cache
128 KB (per SM)
512 KB
L2 Cache
64 MB
Theoretical Performance
16.61 GPixel/s
Pixel Rate
189.8 GPixel/s
24.91 GTexel/s
Texture Rate
515.3 GTexel/s
12.46 GFLOPS
FP16 (half)
32.98 TFLOPS
797.2 GFLOPS
FP32 (float)
32.98 TFLOPS
24.91 GFLOPS
FP64 (double)
515.3 GFLOPS
Board Design
10W
TDP
120W
No outputs
Outputs
Portable Device Dependent
None
Power Connectors
None
Graphics Processor
GP108B
GPU Name
AD103
-
GPU Variant
GN21-X11
Pascal
Architecture
Ada Lovelace
Samsung
Foundry
TSMC
14 nm
Process Size
5 nm
1.8 billion
Transistors
45.9 billion
74 mm²
Die Size
379 mm²
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
6.1
CUDA
8.9
6.4
Shader Model
6.8
