GeForce RTX 5090: specs and benchmarks

VS

Summary

NVIDIA started GeForce RTX 5090 sales on 2025. This is a desktop graphics card based on a Blackwell 2.0 architecture and made with 0 nm manufacturing process. It is primarily aimed at gamer market. 28 GB of GDDR7 memory clocked at 5 GB/s are supplied, and together with 448 Bit memory interface this creates a bandwidth of 280.0 GB/s.

Compatibility-wise, this is triple-slot card attached via PCIe 5.0 x16 interface. Its manufacturer default version has a length of 304 mm. 1x 16-pin power connector is required, and power consumption is at 500 Watt.

Primary details

Some basic facts about GeForce RTX 5090: architecture, market segment, release date etc.

Place in performance rankingnot rated
Place by popularitynot in top-100
ArchitectureBlackwell 2.0
GPU code nameGB202
Market segmentDesktop
Release date2025 (recently)

Detailed specifications

GeForce RTX 5090's specs such as number of shaders, GPU base clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of GeForce RTX 5090's performance, but for precise assessment you have to consider its benchmark and gaming test results.

Pipelines / CUDA cores20480
Boost clock speed2520 MHzof 3599 (Radeon RX 7990 XTX)
Manufacturing process technology0 nmof 4 (Radeon 780M)
Power consumption (TDP)500 Wattof 2400 (Data Center GPU Max Subsystem)
Texture fill rate1,613of 969.9 (H100 SXM5 96 GB)

Form factor & compatibility

This section provides details about the physical dimensions of GeForce RTX 5090 and its compatibility with other computer components. This information is useful when selecting a computer configuration or upgrading an existing one. For desktop graphics cards, it includes details about the interface and bus (for motherboard compatibility) and additional power connectors (for power supply compatibility).

InterfacePCIe 5.0 x16
Length304 mm
Width3-slot
Supplementary power connectors1x 16-pin

VRAM capacity and type

Parameters of memory installed on GeForce RTX 5090: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors have no dedicated memory and use a shared part of system RAM instead.

Memory typeGDDR7
Maximum RAM amount28 GBof 192 (Radeon Instinct MI300X)
Memory bus width448 Bitof 8192 (Radeon Instinct MI250X)
Memory clock speed5 GB/sof 23000 (GeForce RTX 4080 SUPER)
Memory bandwidth280.0 GB/sof 3276 (Aldebaran)

Connectivity and outputs

Types and number of video connectors present on GeForce RTX 5090. As a rule, this section is relevant only for desktop reference graphics cards, since for notebook ones the availability of certain video outputs depends on the laptop model, while non-reference desktop models can (though not necessarily will) bear a different set of video ports.

Display Connectors1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI+

API compatibility

APIs supported by GeForce RTX 5090, sometimes including their particular versions.

DirectX12 Ultimate (12_2)
Shader Model6.7
OpenGL4.6
OpenCL3.0
Vulkan1.3
CUDA9.1

Benchmark performance

Synthetic benchmark performance of GeForce RTX 5090. The combined score is measured on a 0-100 point scale.


We have no data on GeForce RTX 5090 benchmark results.


Recommended processors

These processors are most commonly used with GeForce RTX 5090 according to our statistics.

Community ratings

Here you can see the user rating of the graphics card, as well as rate it yourself.


2.1 15 votes

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

  • 1
  • 2
  • 3
  • 4
  • 5

Questions & comments

Here you can ask a question about GeForce RTX 5090, agree or disagree with our judgements, or report an error or mismatch.