GPUs

ASRock Radeon RX 6900 XT OC Formula vs NVIDIA GeForce RTX 3080 10GB Full Specs

5,120 Shaders
2.48GHz
8,704 Shaders
1.71GHz
16GB GDDR6512GB/s
10GB GDDR6X760.3GB/s
··
25.34 TFLOPS
··
29.77 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
390W
TDP
320W
Power Connectors
-
3x 8-Pin
Power Connectors
1x 12-Pin
-

Radeon RX 6900 XT OC FormulaRadeon RX 6900 XT OC Formula50.69 TFLOPSFP16
x1
GeForce RTX 3080 10GBGeForce RTX 3080 10GB952.6 TOPSINT4 Tensor Sparse
x18.79

Clock Speed
···
Clock Speed
···
Peak OPS
50.69 TFLOPSFP16
Peak OPS
952.6 TOPSINT4 Tensor Sparse
-
Tensor FP16-16
119.1 TFLOPS
FP16-16 Tensor Sparse
238.1 TFLOPS
Tensor FP16-32
59.54 TFLOPS
FP16-32 Tensor Sparse
119.1 TFLOPS
-
BF16
29.77 TFLOPS
Tensor BF16
59.54 TFLOPS
BF16 Tensor Sparse
119.1 TFLOPS
Tensor TF32
-
Tensor TF32
29.77 TFLOPS
FP32
25.34 TFLOPS
FP32
29.77 TFLOPS
FP64
1.58 TFLOPS
FP64
465.1 GFLOPS
Tensor INT4
-
Tensor INT4
476.3 TOPS
-
Tensor INT8
238.1 TOPS
Ray
-
Ray
44.9 TOPS
Pixel Rate
316.8 GPixel/s
Pixel Rate
164.2 GPixel/s
Texture Rate
792 GTexel/s
Texture Rate
465.1 GTexel/s

Shaders
5,120 Shaders
Shaders
8,704 Shaders
TMUs
320 TMUs
TMUs
272 TMUs
ROPs
128 ROPs
ROPs
96 ROPs
Tensor Cores
-
Tensor Cores
272 T-Cores
RT Cores
80 RT-Cores
RT Cores
68 RT-Cores
CUs
80 CUs
SMs
68 SMs

Base Clock
2.13GHz
Base Clock
1.44GHz
Boost Clock
2.48GHz
Boost Clock
1.71GHz

L2 Cache
4.1MB shared
L2 Cache
5.1MB shared
L3 Cache
128MB shared
L3 Cache
-
L3 Bandwidth
1.66TB/s
L3 Bandwidth
-

16GB GDDR6
10GB GDDR6X
Memory Bus
256-bit
Memory Bus
320-bit
Memory Speed
16GT/s
Memory Speed
19GT/s
Memory Bandwidth
512GB/s
Memory Bandwidth
760.3GB/s

TDP
390W
TDP
320W
Max Temp
110°C Max
Max Temp
93°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
VCN 3.0
Encoder Model
NVENC 7

Decoder Model
VCN 3.0
Decoder Model
NVDEC 5

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
3-Slots
PCIe
2-Slots
Height
137 mm (5.39")
Width
332 mm (13.07")
Depth
61 mm (2.4")
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
3x 8-Pin
Power Connectors
1x 12-Pin

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
Radeon 2020 branding
Branding
GeForce RTX 2018 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 17, 2020

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

No images available
No images available