EVGA GeForce RTX 3090 XC3 ULTRA vs NVIDIA GeForce RTX 4090 D Full Specs

Summary

10,496 Shaders 1.73GHz	14,592 Shaders 2.52GHz
24GB GDDR6X936.2GB/s	24GB GDDR6X1.01TB/s
Peak·FP32·FP16 36.21 TFLOPS	Peak·FP32·FP16 73.54 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 350W	TDP 450W
Power Connectors - 2x 8-Pin	Power Connectors 1x 16-Pin 12VHPWR -

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

GeForce RTX 3090 XC3 ULTRA1.16 POPSINT4 Tensor Sparse

x1

GeForce RTX 4090 D2.35 POPSINT4 Tensor Sparse

x2.03

Show Top Score

Theoretical Performance

Clock Speed1725MHz UC·Base·Boost·OC	Clock Speed2520MHz UC·Base·Boost·OC
Peak OPS 1.16 POPSINT4 Tensor Sparse	Peak OPS 2.35 POPSINT4 Tensor Sparse
-	Tensor FP8-16 588.3 TFLOPS FP8-16 Tensor Sparse 1.18 PFLOPS Tensor FP8-32 294.2 TFLOPS FP8-32 Tensor Sparse 588.3 TFLOPS
Tensor FP16-16 144.8 TFLOPS FP16-16 Tensor Sparse 289.7 TFLOPS Tensor FP16-32 72.42 TFLOPS FP16-32 Tensor Sparse 144.8 TFLOPS	Tensor FP16-16 294.2 TFLOPS FP16-16 Tensor Sparse 588.3 TFLOPS Tensor FP16-32 147.1 TFLOPS FP16-32 Tensor Sparse 294.2 TFLOPS
BF16 36.21 TFLOPS Tensor BF16 72.42 TFLOPS BF16 Tensor Sparse 144.8 TFLOPS	BF16 73.54 TFLOPS Tensor BF16 147.1 TFLOPS BF16 Tensor Sparse 294.2 TFLOPS
Tensor TF32 36.21 TFLOPS	Tensor TF32 73.54 TFLOPS
FP32 36.21 TFLOPS	FP32 73.54 TFLOPS
FP64 565.8 GFLOPS	FP64 1.15 TFLOPS
Tensor INT4 579.4 TOPS	Tensor INT4 1.18 POPS
Tensor INT8 289.7 TOPS	Tensor INT8 588.3 TOPS
Ray 54.61 TOPS	Ray 170 TOPS
Pixel Rate 193.2 GPixel/s	Pixel Rate 443.5 GPixel/s
Texture Rate 565.8 GTexel/s	Texture Rate 1.15 TTexel/s

Core Config

Shaders 10,496 Shaders	Shaders 14,592 Shaders
TMUs 328 TMUs	TMUs 456 TMUs
ROPs 112 ROPs	ROPs 176 ROPs
Tensor Cores 328 T-Cores	Tensor Cores 456 T-Cores
RT Cores 82 RT-Cores	RT Cores 114 RT-Cores
SMs 82 SMs	SMs 114 SMs

Clocks

Base Clock 1.4GHz	Base Clock 2.23GHz
Boost Clock 1.73GHz	Boost Clock 2.52GHz

Cache

L2 Cache 6.1MB shared

L2 Cache 73.7MB shared

Memory

24GB GDDR6X	24GB GDDR6X
Memory Bus 384-bit	Memory Bus 384-bit
Memory Speed 19.5GT/s	Memory Speed 21GT/s
Memory Bandwidth 936.2GB/s	Memory Bandwidth 1.01TB/s
ECC No	ECC No

Power & Thermals

TDP 350W	TDP 450W
Max Temp 93°C Max	Max Temp 90°C Max

Video Output

Multi-Monitor 4	Multi-Monitor 4
HDCP HDCP 2.3	HDCP HDCP 2.3

Ports

3x DisplayPort 1.4	3x DisplayPort 1.4
1x HDMI 2.1	1x HDMI 2.1

Encoder

Encoder Model NVENC 7

Encoder Model 2x NVENC 8

Decoder

Decoder Model NVDEC 5

Decoder Model NVDEC 5

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 2.3-Slots	PCIe 3-Slots
Height 126.4 mm (4.98") Width 285.4 mm (11.24") Depth 45.9 mm (1.81")	Height 137 mm (5.39") Width 304 mm (11.97") Depth 61 mm (2.4")
Cooling Open-Air 3x Fans	Cooling Open-Air 2x Fans
Power Connectors 2x 8-Pin	Power Connectors 1x 16-Pin 12VHPWR

Chip

Manufacturer EVGA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ampere	Architecture Ada Lovelace
Family GeForce 30	Family GeForce 40
Branding	Branding
Codename NV172	Codename NV182
Chip Variant GA102-200-KD-A1	Chip Variant AD102-200-A1
Market Segment Desktop	Market Segment Desktop
Release Date Sep 24, 2020	Release Date Dec 28, 2023

Fabrication

Foundry Samsung	Foundry TSMC
Fabrication Node 8N	Fabrication Node 4N
Die Size 628mm²	Die Size 608mm²
Transistor Count 28.3 Billion	Transistor Count 76.3 Billion
Transistor Density 45.04 MTr/mm²	Transistor Density 125.4 MTr/mm²

Images

No images available

No images available

Competitors

EVGAGeForce RTX 3090 XC3 ULTRA vs GPU NVIDIAGeForce RTX 4070 Ti Super EVGAGeForce RTX 3090 XC3 ULTRA vs GPU NVIDIAGeForce RTX 5080 EVGAGeForce RTX 3090 XC3 ULTRA vs GPU NVIDIAGeForce RTX 4080 Super Show 12 more

NVIDIAGeForce RTX 4090 D vs GPU NVIDIAGeForce RTX 4080 Super NVIDIAGeForce RTX 4090 D vs GPU NVIDIAGeForce RTX 5090 D v2 NVIDIAGeForce RTX 4090 D vs GPU NVIDIAGeForce RTX 5080 Show 12 more