NVIDIA GeForce RTX 5090 Mobile vs NVIDIA GeForce GTX 670MX
We compared two Mobile platform GPUs: 24GB VRAM GeForce RTX 5090 Mobile and 3GB VRAM GeForce GTX 670MX 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 12 years and 5 months late
Boost Clock1515MHz
More VRAM (24GB vs 3GB)
Larger VRAM bandwidth (896.0GB/s vs 67.20GB/s)
9536 additional rendering cores
NVIDIA GeForce GTX 670MX 's Advantages
Lower TDP (75W vs 95W)
Score
Benchmark
FP32 (float)
GeForce RTX 5090 Mobile
+2655%
31.8 TFLOPS
GeForce GTX 670MX
1.154 TFLOPS
Graphics Card
Mar 2025
Release Date
Oct 2012
GeForce 50 Mobile
Generation
GeForce 600M
Mobile
Type
Mobile
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
990 MHz
Base Clock
-
1515 MHz
Boost Clock
-
1750 MHz
Memory Clock
700 MHz
Memory
24GB
Memory Size
3GB
GDDR7
Memory Type
GDDR5
256bit
Memory Bus
192bit
896.0GB/s
Bandwidth
67.20GB/s
Render Config
-
-
-
82
SM Count
-
10496
Shading Units
960
328
TMUs
80
112
ROPs
24
328
Tensor Cores
-
82
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per SMX)
64 MB
L2 Cache
384 KB
-
-
-
Theoretical Performance
169.7 GPixel/s
Pixel Rate
12.02 GPixel/s
496.9 GTexel/s
Texture Rate
48.08 GTexel/s
31.80 TFLOPS
FP16 (half)
-
31.80 TFLOPS
FP32 (float)
1154 GFLOPS
496.9 GFLOPS
FP64 (double)
48.08 GFLOPS
Board Design
95W
TDP
75W
550 W
Suggested PSU
-
Portable Device Dependent
Outputs
No outputs
None
Power Connectors
-
Graphics Processor
GB203
GPU Name
GK104
GN22-X11-A1
GPU Variant
N13E-GR-A2
Blackwell 2.0
Architecture
Kepler
TSMC
Foundry
TSMC
5 nm
Process Size
28 nm
45.6 billion
Transistors
3.54 billion
378 mm²
Die Size
294 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.4
Vulkan
1.1
12.0
CUDA
3.0
6.8
Shader Model
5.1
