Report an Error

NVIDIA GeForce RTX 5090 D

Graphics Processor
GB202
Cores
21760
TMUs
680
ROPs
192
Memory Size
32 GB
Memory Type
GDDR7
Bus Width
512 bit
Back
Back
This product is not released yet.
Data on this page may change in the future.
The GeForce RTX 5090 D will be a graphics card by NVIDIA, that is expected to launch on January 30th, 2025. Built on the 4 nm process, and based on the GB202 graphics processor, the card supports DirectX 12 Ultimate. This ensures that all modern games will run on GeForce RTX 5090 D. Additionally, the DirectX 12 Ultimate capability guarantees support for hardware-raytracing, variable-rate shading and more, in upcoming video games. It features 21760 shading units, 680 texture mapping units, and 192 ROPs. Also included are 680 tensor cores which help improve the speed of machine learning applications. The card also has 170 raytracing acceleration cores. NVIDIA has paired 32 GB GDDR7 memory with the GeForce RTX 5090 D, which are connected using a 512-bit memory interface. The GPU is operating at a frequency of 2017 MHz, which can be boosted up to 2407 MHz, memory is running at 2209 MHz (28 Gbps effective).
Being a dual-slot card, the NVIDIA GeForce RTX 5090 D draws power from 1x 16-pin power connector, with power draw rated at 575 W maximum. Display outputs include: 1x HDMI 2.1b, 3x DisplayPort 2.1b. GeForce RTX 5090 D is connected to the rest of the system using a PCI-Express 5.0 x16 interface. The card's dimensions are 304 mm x 137 mm x 48 mm, and it features a dual-slot cooling solution.

Graphics Processor

GPU Name
GB202
Architecture
Blackwell 2.0
Foundry
TSMC
Process Size
4 nm
Transistors
92,000 million
Die Size
unknown

Graphics Card

Release Date
Jan 30th, 2025
Announced
Jan 7th, 2025
Generation
GeForce 50
Predecessor
GeForce 40
Production
Unreleased
Bus Interface
PCIe 5.0 x16

Clock Speeds

Base Clock
2017 MHz
Boost Clock
2407 MHz
Memory Clock
2209 MHz
28 Gbps effective

Memory

Memory Size
32 GB
Memory Type
GDDR7
Memory Bus
512 bit
Bandwidth
1.79 TB/s

Render Config

Shading Units
21760
TMUs
680
ROPs
192
SM Count
170
Tensor Cores
680
RT Cores
170
L1 Cache
128 KB (per SM)
L2 Cache
88 MB

Theoretical Performance

Pixel Rate
462.1 GPixel/s
Texture Rate
1,637 GTexel/s
FP16 (half)
104.8 TFLOPS (1:1)
FP32 (float)
104.8 TFLOPS
FP64 (double)
1.637 TFLOPS (1:64)

Board Design

Slot Width
Dual-slot
Length
304 mm
12 inches
Width
137 mm
5.4 inches
Height
48 mm
1.9 inches
TDP
575 W
Suggested PSU
950 W
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1b
Power Connectors
1x 16-pin
Board Number
PG145 SKU 30

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.4
CUDA
10.1
Shader Model
6.8

GB202 GPU Notes

Ray Tracing Cores: 4th Gen
Tensor Cores: 5th Gen
NVENC: 9th Gen
NVDEC: 6th Gen
PureVideo HD: VP13
VDPAU: Feature Set M

Latest Drivers:
Windows 10 / 11:
GeForce Release: Latest
Quadro Release: Latest
Data Center Release: Latest

Retail boards based on this design (3)

Name GPU Clock Boost Clock Memory Clock Other Changes
2017 MHz 2407 MHz 2209 MHz Triple-slot
2017 MHz 2407 MHz 2209 MHz 326 mm/12.8 inches, Triple-slot
2017 MHz 2407 MHz 2209 MHz Triple-slot
Jan 9th, 2025 04:51 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts