GeForce RTX 5090 Mobile vs GTX 645 OEM

#ad 
Buy on Amazon
VS

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the rankingnot rated22
Place by popularitynot in top-100not in top-100
Power efficiencyno data56.52
ArchitectureKepler (2012−2018)Blackwell 2.0 (2025−2026)
GPU code nameGK106GB203
Market segmentDesktopLaptop
Release date22 April 2013 (12 years ago)27 March 2025 (less than a year ago)

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores57610496
Core clock speed824 MHz990 MHz
Boost clock speedno data1515 MHz
Number of transistors2,540 million45,600 million
Manufacturing process technology28 nm5 nm
Power consumption (TDP)65 Watt95 Watt
Texture fill rate39.55496.9
Floating-point processing power0.9492 TFLOPS31.8 TFLOPS
ROPs16112
TMUs48328
Tensor Coresno data328
Ray Tracing Coresno data82
L1 Cache48 KB10.3 MB
L2 Cache256 KB64 MB

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Laptop sizeno datalarge
InterfacePCIe 3.0 x16PCIe 5.0 x16
Length147 mmno data
Width1-slotno data
Supplementary power connectorsNoneno data

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory typeGDDR5GDDR7
Maximum RAM amount1 GB24 GB
Memory bus width128 Bit256 Bit
Memory clock speed1000 MHz1750 MHz
Memory bandwidth64 GB/s896.0 GB/s
Shared memory--
Resizable BAR-+

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display Connectors1x DVI, 1x HDMI, 1x DisplayPortPortable Device Dependent
HDMI+-

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX12 (11_0)12 Ultimate (12_2)
Shader Model5.16.8
OpenGL4.64.6
OpenCL1.23.0
Vulkan1.1.1261.4
CUDA3.012.0
DLSS-+

Pros & cons summary


Recency 22 April 2013 27 March 2025
Maximum RAM amount 1 GB 24 GB
Chip lithography 28 nm 5 nm
Power consumption (TDP) 65 Watt 95 Watt

GTX 645 OEM has 46.2% lower power consumption.

RTX 5090 Mobile, on the other hand, has an age advantage of 11 years, a 2300% higher maximum VRAM amount, and a 460% more advanced lithography process.

We couldn't decide between GeForce GTX 645 OEM and GeForce RTX 5090 Mobile. We've got no test results to judge.

Be aware that GeForce GTX 645 OEM is a desktop graphics card while GeForce RTX 5090 Mobile is a notebook one.

Vote for your favorite

Do you think we are right or mistaken in our choice? Vote by clicking "Like" button near your favorite graphics card.


NVIDIA GeForce GTX 645 OEM
GeForce GTX 645 OEM
NVIDIA GeForce RTX 5090 Mobile
GeForce RTX 5090 Mobile

Other comparisons

We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.

Community ratings

Here you can see the user ratings of the compared graphics cards, as well as rate them yourself.


3.7 111 votes

Rate GeForce GTX 645 OEM on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
3.8 237 votes

Rate GeForce RTX 5090 Mobile on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Comments

Here you can give us your opinion about GeForce GTX 645 OEM or GeForce RTX 5090 Mobile, agree or disagree with our ratings, or report errors or inaccuracies on the site.