GPUs

NVIDIA GeForce RTX 3080 Ti vs PowerColor Radeon RX 6800 Red Dragon Full Specs

10,240 Shaders
1.67GHz
3,840 Shaders
2.17GHz
12GB GDDR6X912.4GB/s
16GB GDDR6512GB/s
··
34.1 TFLOPS
··
16.67 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
350W
TDP
250W
Power Connectors
1x 12-Pin
-
Power Connectors
-
2x 8-Pin

GeForce RTX 3080 TiGeForce RTX 3080 Ti1.09 POPSINT4 Tensor Sparse
x32.74
Radeon RX 6800 Red DragonRadeon RX 6800 Red Dragon33.33 TFLOPSFP16
x1

Clock Speed
···
Clock Speed
···
Peak OPS
1.09 POPSINT4 Tensor Sparse
Peak OPS
33.33 TFLOPSFP16
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
34.1 TFLOPS
Tensor BF16
68.2 TFLOPS
BF16 Tensor Sparse
136.4 TFLOPS
-
Tensor TF32
34.1 TFLOPS
Tensor TF32
-
FP32
34.1 TFLOPS
FP32
16.67 TFLOPS
FP64
532.8 GFLOPS
FP64
1.04 TFLOPS
Tensor INT4
545.6 TOPS
Tensor INT4
-
Tensor INT8
272.8 TOPS
-
Ray
51.43 TOPS
Ray
-
Pixel Rate
186.5 GPixel/s
Pixel Rate
208.3 GPixel/s
Texture Rate
532.8 GTexel/s
Texture Rate
520.8 GTexel/s

Shaders
10,240 Shaders
Shaders
3,840 Shaders
TMUs
320 TMUs
TMUs
240 TMUs
ROPs
112 ROPs
ROPs
96 ROPs
Tensor Cores
320 T-Cores
Tensor Cores
-
RT Cores
80 RT-Cores
RT Cores
60 RT-Cores
SMs
80 SMs
CUs
60 CUs

Base Clock
1.4GHz
Base Clock
1.85GHz
Boost Clock
1.67GHz
Boost Clock
2.17GHz

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

12GB GDDR6X
16GB GDDR6
Memory Bus
384-bit
Memory Bus
256-bit
Memory Speed
19GT/s
Memory Speed
16GT/s
Memory Bandwidth
912.4GB/s
Memory Bandwidth
512GB/s
ECC
No
ECC
No

TDP
350W
TDP
250W
Max Temp
93°C Max
Max Temp
110°C Max

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

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

Encoder Model
NVENC 7
Encoder Model
VCN 3.0

Decoder Model
NVDEC 5
Decoder Model
VCN 3.0

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
2-Slots
PCIe
2.7-Slots
Height
112 mm (4.41")
Width
285 mm (11.22")
Depth
40 mm (1.57")
Height
135 mm (5.32")
Width
310 mm (12.2")
Depth
54 mm (2.13")
Cooling
Open-Air
2x Fans
Cooling
Open-Air
3x Fans
Power Connectors
1x 12-Pin
Power Connectors
2x 8-Pin

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
GeForce RTX 2018 branding
Branding
Radeon 2020 branding
Codename
NV172
Codename
Sienna Cichlid
Chip Variant
GA102-200-KD-A1
Chip Variant
Navi 21 XL
Market Segment
Desktop
Market Segment
Desktop
Release Date
Jun 3, 2021
Release Date
Nov 18, 2020

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

No images available
No images available