AMD Radeon RX 6900 XT vs EVGA GeForce RTX 3090 FTW3 ULTRA Full Specs

Summary

5,120 Shaders 2.25GHz	10,496 Shaders 1.8GHz
16GB GDDR6512GB/s	24GB GDDR6X936.2GB/s
Peak·FP32·FP16 23.04 TFLOPS	Peak·FP32·FP16 37.79 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 300W	TDP 350W
Power Connectors 2x 8-Pin	Power Connectors 3x 8-Pin

Highlights

Peak OPS

Peak OPS FP32 FP16 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

Radeon RX 6900 XT46.08 TFLOPSFP16

x1

GeForce RTX 3090 FTW3 ULTRA1.21 POPSINT4 Tensor Sparse

x26.24

Show Top Score

Theoretical Performance

Clock Speed2250MHz UC·Base·Boost·OC	Clock Speed1800MHz UC·Base·Boost·OC
Peak OPS 46.08 TFLOPSFP16	Peak OPS 1.21 POPSINT4 Tensor Sparse
-	Tensor FP16-16 151.1 TFLOPS FP16-16 Tensor Sparse 302.3 TFLOPS Tensor FP16-32 75.57 TFLOPS FP16-32 Tensor Sparse 151.1 TFLOPS
-	BF16 37.79 TFLOPS Tensor BF16 75.57 TFLOPS BF16 Tensor Sparse 151.1 TFLOPS
Tensor TF32 -	Tensor TF32 37.79 TFLOPS
FP32 23.04 TFLOPS	FP32 37.79 TFLOPS
FP64 1.44 TFLOPS	FP64 590.4 GFLOPS
Tensor INT4 -	Tensor INT4 604.6 TOPS
-	Tensor INT8 302.3 TOPS
Ray -	Ray 56.99 TOPS
Pixel Rate 288 GPixel/s	Pixel Rate 201.6 GPixel/s
Texture Rate 720 GTexel/s	Texture Rate 590.4 GTexel/s

Core Config

Shaders 5,120 Shaders	Shaders 10,496 Shaders
TMUs 320 TMUs	TMUs 328 TMUs
ROPs 128 ROPs	ROPs 112 ROPs
Tensor Cores -	Tensor Cores 328 T-Cores
RT Cores 80 RT-Cores	RT Cores 82 RT-Cores
CUs 80 CUs	SMs 82 SMs

Clocks

Base Clock 1.82GHz	Base Clock 1.4GHz
Boost Clock 2.25GHz	Boost Clock 1.8GHz

Cache

L2 Cache 4.1MB shared	L2 Cache 6.1MB shared
L3 Cache 128MB shared	L3 Cache -
L3 Bandwidth 1.66TB/s	L3 Bandwidth -

Memory

16GB GDDR6	24GB GDDR6X
Memory Bus 256-bit	Memory Bus 384-bit
Memory Speed 16GT/s	Memory Speed 19.5GT/s
Memory Bandwidth 512GB/s	Memory Bandwidth 936.2GB/s

Power & Thermals

TDP 300W	TDP 350W
Max Temp 110°C Max	Max Temp 93°C Max

Video Output

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

Ports

2x DisplayPort 1.4	3x DisplayPort 1.4
1x HDMI 2.1	1x HDMI 2.1
1x USB-C	-

Encoder

Encoder Model VCN 3.0

Encoder Model NVENC 7

Decoder

Decoder Model VCN 3.0

Decoder Model NVDEC 5

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 2.5-Slots	PCIe 2.8-Slots
Height 120 mm (4.72") Width 267 mm (10.51") Depth 50 mm (1.97")	Height 136.8 mm (5.39") Width 300 mm (11.81") Depth 56.4 mm (2.22")
Cooling Open-Air 3x Fans	Cooling Open-Air 3x Fans
Power Connectors 2x 8-Pin	Power Connectors 3x 8-Pin

Chip

Manufacturer AMD	Manufacturer EVGA
Chip Designer AMD	Chip Designer NVIDIA
Architecture RDNA 2	Architecture Ampere
Family Radeon RX 6000	Family GeForce 30
Branding	Branding
Codename Sienna Cichlid	Codename NV172
Chip Variant Navi 21 XL	Chip Variant GA102-200-KD-A1
Market Segment Desktop	Market Segment Desktop
Release Date Dec 8, 2020	Release Date Sep 24, 2020

Fabrication

Foundry TSMC	Foundry Samsung
Fabrication Node N7	Fabrication Node 8N
Die Size 520mm²	Die Size 628mm²
Transistor Count 26.8 Billion	Transistor Count 28.3 Billion
Transistor Density 51.56 MTr/mm²	Transistor Density 45.04 MTr/mm²

Images

No images available

No images available

Used In

Desktops XPS(XD8950, Late 2021)Aurora(R13, Late 2021)Aurora(R14, Late 2021)

Desktops -

Competitors

AMDRadeon RX 6900 XT vs GPU NVIDIAGeForce RTX 4070 Ti Super AMDRadeon RX 6900 XT vs GPU NVIDIAGeForce RTX 4080 Super AMDRadeon RX 6900 XT vs GPU NVIDIAGeForce RTX 5070 Ti Show 12 more

EVGAGeForce RTX 3090 FTW3 ULTRA vs GPU NVIDIAGeForce RTX 4070 Ti Super EVGAGeForce RTX 3090 FTW3 ULTRA vs GPU NVIDIAGeForce RTX 5080 EVGAGeForce RTX 3090 FTW3 ULTRA vs GPU NVIDIAGeForce RTX 4080 Super Show 12 more