GIGABYTE GeForce RTX 3090 Ti Gaming OC vs NVIDIA GeForce RTX 3080 Ti Full Specs

Summary

10,752 Shaders 1.91GHz	10,240 Shaders 1.67GHz
24GB GDDR6X1.01TB/s	12GB GDDR6X912.4GB/s
Peak·FP32·FP16 40.97 TFLOPS	Peak·FP32·FP16 34.1 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 450W	TDP 350W
Power Connectors 1x 16-Pin 12VHPWR -	Power Connectors - 1x 12-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

GeForce RTX 3090 Ti Gaming OC1.31 POPSINT4 Tensor Sparse

x1.20

GeForce RTX 3080 Ti1.09 POPSINT4 Tensor Sparse

x1

Show Top Score

Theoretical Performance

Clock Speed1905MHz UC·Base·Boost·OC	Clock Speed1665MHz UC·Base·Boost·OC
Peak OPS 1.31 POPSINT4 Tensor Sparse	Peak OPS 1.09 POPSINT4 Tensor Sparse
Tensor FP16-16 163.9 TFLOPS FP16-16 Tensor Sparse 327.7 TFLOPS Tensor FP16-32 81.93 TFLOPS FP16-32 Tensor Sparse 163.9 TFLOPS	Tensor FP16-16 136.4 TFLOPS FP16-16 Tensor Sparse 272.8 TFLOPS Tensor FP16-32 68.2 TFLOPS FP16-32 Tensor Sparse 136.4 TFLOPS
BF16 40.97 TFLOPS Tensor BF16 81.93 TFLOPS BF16 Tensor Sparse 163.9 TFLOPS	BF16 34.1 TFLOPS Tensor BF16 68.2 TFLOPS BF16 Tensor Sparse 136.4 TFLOPS
Tensor TF32 40.97 TFLOPS	Tensor TF32 34.1 TFLOPS
FP32 40.97 TFLOPS	FP32 34.1 TFLOPS
FP64 640.1 GFLOPS	FP64 532.8 GFLOPS
Tensor INT4 655.4 TOPS	Tensor INT4 545.6 TOPS
Tensor INT8 327.7 TOPS	Tensor INT8 272.8 TOPS
Ray 61.78 TOPS	Ray 51.43 TOPS
Pixel Rate 213.4 GPixel/s	Pixel Rate 186.5 GPixel/s
Texture Rate 640.1 GTexel/s	Texture Rate 532.8 GTexel/s

Core Config

Shaders 10,752 Shaders	Shaders 10,240 Shaders
TMUs 336 TMUs	TMUs 320 TMUs
ROPs 112 ROPs	ROPs 112 ROPs
Tensor Cores 336 T-Cores	Tensor Cores 320 T-Cores
RT Cores 84 RT-Cores	RT Cores 80 RT-Cores
SMs 84 SMs	SMs 80 SMs

Clocks

Base Clock 1.56GHz	Base Clock 1.4GHz
Boost Clock 1.91GHz	Boost Clock 1.67GHz

Cache

L2 Cache 6.1MB shared

L2 Cache 6.1MB shared

Memory

24GB GDDR6X	12GB GDDR6X
Memory Bus 384-bit	Memory Bus 384-bit
Memory Speed 21GT/s	Memory Speed 19GT/s
Memory Bandwidth 1.01TB/s	Memory Bandwidth 912.4GB/s
ECC No	ECC No

Power & Thermals

TDP 450W	TDP 350W
Max Temp 92°C Max	Max Temp 93°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 NVENC 7

Decoder

Decoder Model NVDEC 5

Decoder Model NVDEC 5

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 3.4-Slots	PCIe 2-Slots
Height 150 mm (5.91") Width 331 mm (13.03") Depth 70 mm (2.76")	Height 112 mm (4.41") Width 285 mm (11.22") Depth 40 mm (1.57")
Cooling Open-Air 3x Fans	Cooling Open-Air 2x Fans
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors 1x 12-Pin

Chip

Manufacturer GIGABYTE	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ampere	Architecture Ampere
Family GeForce 30	Family GeForce 30
Branding	Branding
Codename NV172	Codename NV172
Chip Variant GA102-200-KD-A1	Chip Variant GA102-200-KD-A1
Market Segment Desktop	Market Segment Desktop
Release Date Mar 29, 2022	Release Date Jun 3, 2021

Fabrication

Foundry Samsung	Foundry Samsung
Fabrication Node 8N	Fabrication Node 8N
Die Size 628mm²	Die Size 628mm²
Transistor Count 28.3 Billion	Transistor Count 28.3 Billion
Transistor Density 45.04 MTr/mm²	Transistor Density 45.04 MTr/mm²

Images

No images available

No images available

Used In

Desktops -

Desktops XPS(XD8950, Late 2021)Aurora(R13, Late 2021)Aurora(R14, Late 2021) Show 6 more

Competitors

GIGABYTEGeForce RTX 3090 Ti Gaming OC vs GPU NVIDIAGeForce RTX 4090 D GIGABYTEGeForce RTX 3090 Ti Gaming OC vs GPU NVIDIAGeForce RTX 5080 GIGABYTEGeForce RTX 3090 Ti Gaming OC vs GPU NVIDIAGeForce RTX 5090 D v2 Show 12 more

NVIDIAGeForce RTX 3080 Ti vs GPU AMDRadeon RX 9070 XT NVIDIAGeForce RTX 3080 Ti vs GPU AMDRadeon RX 7900 GRE NVIDIAGeForce RTX 3080 Ti vs GPU NVIDIAGeForce RTX 5080 Show 12 more