Report an Error

NVIDIA GeForce RTX 4090 D

Graphics Processor
AD102
Cores
14592
TMUs
456
ROPs
176
Memory Size
24 GB
Memory Type
GDDR6X
Bus Width
384 bit
GPU Chip
GPU
I/O
I/O
Rear
Rear
Back
Back
The GeForce RTX 4090 D is an enthusiast-class graphics card by NVIDIA, launched on December 28th, 2023. Built on the 5 nm process, and based on the AD102 graphics processor, in its AD102-250-A1 variant, the card supports DirectX 12 Ultimate. This ensures that all modern games will run on GeForce RTX 4090 D. Additionally, the DirectX 12 Ultimate capability guarantees support for hardware-raytracing, variable-rate shading and more, in upcoming video games. The AD102 graphics processor is a large chip with a die area of 609 mm² and 76,300 million transistors. Unlike the fully unlocked TITAN Ada, which uses the same GPU but has all 18432 shaders enabled, NVIDIA has disabled some shading units on the GeForce RTX 4090 D to reach the product's target shader count. It features 14592 shading units, 456 texture mapping units, and 176 ROPs. Also included are 456 tensor cores which help improve the speed of machine learning applications. The card also has 114 raytracing acceleration cores. NVIDIA has paired 24 GB GDDR6X memory with the GeForce RTX 4090 D, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 2280 MHz, which can be boosted up to 2520 MHz, memory is running at 1313 MHz (21 Gbps effective).
Being a triple-slot card, the NVIDIA GeForce RTX 4090 D draws power from 1x 16-pin power connector, with power draw rated at 425 W maximum. Display outputs include: 1x HDMI 2.1, 3x DisplayPort 1.4a. GeForce RTX 4090 D is connected to the rest of the system using a PCI-Express 4.0 x16 interface. The card's dimensions are 304 mm x 137 mm x 61 mm, and it features a triple-slot cooling solution. Its price at launch was 1599 US Dollars.

Graphics Processor

GPU Name
AD102
GPU Variant
AD102-250-A1
Architecture
Ada Lovelace
Foundry
TSMC
Process Size
5 nm
Transistors
76,300 million
Density
125.3M / mm²
Die Size
609 mm²

Graphics Card

Release Date
Dec 28th, 2023
Availability
Dec 28th, 2023
Generation
GeForce 40
Predecessor
GeForce 30
Production
Active
Launch Price
1,599 USD
Bus Interface
PCIe 4.0 x16

Relative Performance

GeForce 210
0%
GeForce 9400 GT
0%
Radeon HD 4550
1%
Radeon HD 5450
1%
Radeon HD 6450
1%
GeForce GT 520
1%
GeForce GT 220
1%
GeForce GT 430
1%
Radeon HD 5570
1%
Radeon HD 4670
2%
GeForce GT 440
2%
GeForce GT 240
2%
GeForce 9600 GT
2%
Radeon HD 5670
2%
GeForce GT 640
2%
GeForce 9800 GT
2%
Radeon HD 6670
2%
Radeon HD 4830
2%
Radeon HD 4770
3%
Radeon HD 4850
3%
GeForce GTS 250
3%
GeForce GTS 450
3%
Radeon HD 5750
3%
Radeon HD 7750
3%
Radeon HD 5770
3%
GeForce GTX 260
3%
Radeon HD 4870
3%
Radeon Vega 8
3%
GeForce GTX 550 Ti
4%
GeForce GTX 650
4%
Radeon HD 5830
4%
Radeon HD 6790
4%
Radeon HD 4890
4%
GeForce GTX 460
4%
Radeon RX Vega 11
4%
GeForce GT 1030
4%
GeForce GTX 275
4%
Radeon HD 7770 GHz Edition
4%
GeForce GTX 280
4%
GeForce GTX 465
4%
Radeon HD 6850
5%
GeForce GTX 285
5%
Radeon HD 5850
5%
GeForce GTX 650 Ti
5%
Radeon HD 7790
5%
Radeon RX 550
5%
GeForce GTX 470
5%
Radeon HD 6870
6%
Radeon HD 5870
6%
GeForce GTX 560 Ti
6%
Radeon HD 4870 X2
6%
GeForce GTX 750 Ti
6%
Radeon HD 6950
6%
GeForce GTX 295
6%
GeForce GTX 650 Ti Boost
7%
Radeon HD 7850
7%
GeForce GTX 480
7%
Radeon HD 6970
7%
Radeon R7 265
7%
Radeon RX 460
7%
Radeon R7 370
7%
GeForce GTX 660
7%
GeForce GTX 570
7%
Radeon RX 560
7%
GeForce GTX 950
8%
Radeon HD 7870 GHz Edition
8%
Radeon R9 270X
8%
GeForce GTX 660 Ti
8%
GeForce GTX 580
8%
GeForce GTX 1050
8%
Radeon HD 7950
8%
GeForce GTX 1630
9%
Radeon HD 5970
9%
GeForce GTX 760
9%
GeForce GTX 670
9%
GeForce GTX 960
10%
Radeon R9 380
10%
Radeon R9 285
10%
Radeon HD 7970
10%
GeForce GTX 680
10%
GeForce GTX 1050 Ti
10%
GeForce GTX 770
11%
Radeon HD 6990
11%
Radeon R9 280X
11%
GeForce GTX 590
11%
Radeon HD 7970 GHz Edition
11%
GeForce GTX 780
13%
Arc A380
13%
Radeon RX 6400
13%
GeForce GTX 1650
13%
Radeon RX 470
14%
Radeon R9 290
14%
Radeon RX 570
15%
Radeon R9 390
15%
Radeon R9 290X
15%
GeForce GTX 970
15%
GeForce GTX TITAN
16%
GeForce GTX 780 Ti
16%
Radeon R9 390X
16%
Radeon HD 7990
16%
Radeon RX 480
16%
GeForce GTX 690
16%
GeForce GTX 1060 6 GB
17%
Radeon RX 5500 OEM
17%
Radeon RX 580
17%
Radeon RX 5500 XT
17%
Radeon RX 6500 XT
17%
GeForce GTX 980
18%
GeForce GTX 1650 SUPER
18%
Radeon R9 FURY
18%
Radeon RX 590
19%
Radeon R9 295X2
20%
GeForce GTX 1660
20%
Radeon R9 FURY X
20%
GeForce GTX 980 Ti
20%
GeForce GTX TITAN X
21%
GeForce GTX 1660 SUPER
21%
GeForce GTX 1070
23%
GeForce GTX 1660 Ti
23%
GeForce RTX 3050 8 GB
23%
Radeon RX Vega 56
24%
GeForce GTX 1070 Ti
25%
Radeon RX 5600 XT
26%
Radeon RX Vega 64
26%
GeForce GTX 1080
27%
GeForce RTX 2060
27%
Radeon RX 5700
28%
Arc A580
28%
Radeon RX 6600
29%
GeForce RTX 2060 SUPER
30%
GeForce RTX 2070
30%
Radeon RX 5700 XT
30%
GeForce RTX 3060 12 GB
31%
Arc A750
32%
Radeon VII
32%
TITAN X Pascal
33%
Radeon RX 6600 XT
33%
GeForce GTX 1080 Ti
34%
Arc A770
34%
GeForce RTX 2070 SUPER
34%
Radeon RX 6650 XT
36%
Radeon RX 7600
36%
GeForce RTX 4060
37%
GeForce RTX 2080
37%
Radeon RX 7600 XT
38%
GeForce RTX 2080 SUPER
39%
GeForce RTX 3060 Ti
40%
Radeon RX 6700 XT
41%
Radeon RX 6750 XT
43%
GeForce RTX 4060 Ti 8 GB
44%
GeForce RTX 2080 Ti
44%
GeForce RTX 3070
46%
GeForce RTX 3070 Ti
50%
Radeon RX 7700 XT
50%
Radeon RX 6800
51%
GeForce RTX 4070
57%
Radeon RX 6800 XT
58%
GeForce RTX 3080
60%
Radeon RX 7800 XT
61%
Radeon RX 6900 XT
62%
GeForce RTX 4070 SUPER
66%
Radeon RX 7900 GRE
67%
GeForce RTX 3080 Ti
67%
Radeon RX 6950 XT
67%
GeForce RTX 3090
69%
GeForce RTX 4070 Ti
70%
GeForce RTX 4070 Ti SUPER
77%
Radeon RX 7900 XT
79%
GeForce RTX 3090 Ti
80%
GeForce RTX 4080
89%
GeForce RTX 4080 SUPER
91%
Radeon RX 7900 XTX
92%
GeForce RTX 4090 D
100%
GeForce RTX 4090
112%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
2280 MHz
Boost Clock
2520 MHz
Memory Clock
1313 MHz
21 Gbps effective

Memory

Memory Size
24 GB
Memory Type
GDDR6X
Memory Bus
384 bit
Bandwidth
1.01 TB/s

Render Config

Shading Units
14592
TMUs
456
ROPs
176
SM Count
114
Tensor Cores
456
RT Cores
114
L1 Cache
128 KB (per SM)
L2 Cache
72 MB

Theoretical Performance

Pixel Rate
443.5 GPixel/s
Texture Rate
1,149 GTexel/s
FP16 (half)
73.54 TFLOPS (1:1)
FP32 (float)
73.54 TFLOPS
FP64 (double)
1,149 GFLOPS (1:64)

Board Design

Slot Width
Triple-slot
Length
304 mm
12 inches
Width
137 mm
5.4 inches
Height
61 mm
2.4 inches
TDP
425 W
Suggested PSU
800 W
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
Power Connectors
1x 16-pin
Board Number
PG139 SKU 330

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
8.9
Shader Model
6.7

AD102 GPU Notes

Ray Tracing Cores: 3rd Gen
Tensor Cores: 4th Gen
NVENC: 8th Gen
NVDEC: 5th Gen
PureVideo HD: VP12
VDPAU: Feature Set L

Retail boards based on this design (14)

Name GPU Clock Boost Clock Memory Clock Other Changes
2280 MHz 2520 MHz 1313 MHz 342 mm/13.5 inches
2280 MHz 2520 MHz 1313 MHz 330 mm/13 inches
2280 MHz 2520 MHz 1313 MHz 254 mm/10 inches, Dual-slot
2280 MHz 2520 MHz 1313 MHz 337 mm/13.3 inches
2280 MHz 2520 MHz 1313 MHz 337 mm/13.3 inches
2280 MHz 2520 MHz 1313 MHz 316 mm/12.4 inches
2280 MHz 2520 MHz 1313 MHz 350 mm/13.8 inches, Quad-slot
2280 MHz 2520 MHz 1313 MHz 330 mm/13 inches
2280 MHz 2520 MHz 1313 MHz 342 mm/13.5 inches
2280 MHz 2520 MHz 1313 MHz 352 mm/13.9 inches
2280 MHz 2520 MHz 1313 MHz 394 mm/15.5 inches
2280 MHz 2520 MHz 1313 MHz 322 mm/12.7 inches
2280 MHz 2520 MHz 1313 MHz 336 mm/13.2 inches, Quad-slot
2280 MHz 2520 MHz 1313 MHz 381 mm/15 inches
Apr 27th, 2024 04:45 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts