GPUs

AMD Radeon RX 9070 XT vs NVIDIA GeForce RTX 3080 10GB Full Specs

4,096 Shaders
2.97GHz
8,704 Shaders
1.71GHz
16GB GDDR6640GB/s
10GB GDDR6X760.3GB/s
··
48.66 TFLOPS
··
29.77 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
304W
TDP
320W
Power Connectors
-
2x 8-Pin
Power Connectors
1x 12-Pin
-

Radeon RX 9070 XTRadeon RX 9070 XT1.56 POPSINT4 Tensor Sparse
x1.63
GeForce RTX 3080 10GBGeForce RTX 3080 10GB952.6 TOPSINT4 Tensor Sparse
x1

Clock Speed
···
Clock Speed
···
Peak OPS
1.56 POPSINT4 Tensor Sparse
Peak OPS
952.6 TOPSINT4 Tensor Sparse
Tensor FP8-16
194.6 TFLOPS
FP8-16 Tensor Sparse
389.3 TFLOPS
Tensor FP8-32
194.6 TFLOPS
FP8-32 Tensor Sparse
389.3 TFLOPS
-
Tensor FP16-16
97.32 TFLOPS
FP16-16 Tensor Sparse
194.6 TFLOPS
Tensor FP16-32
97.32 TFLOPS
FP16-32 Tensor Sparse
194.6 TFLOPS
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
97.32 TFLOPS
Tensor BF16
97.32 TFLOPS
BF16 Tensor Sparse
194.6 TFLOPS
BF16
29.77 TFLOPS
Tensor BF16
59.54 TFLOPS
BF16 Tensor Sparse
119.1 TFLOPS
Tensor TF32
-
Tensor TF32
29.77 TFLOPS
FP32
48.66 TFLOPS
FP32
29.77 TFLOPS
FP64
1.52 TFLOPS
FP64
465.1 GFLOPS
Tensor INT4
778.6 TOPS
Tensor INT4
476.3 TOPS
Tensor INT8
389.3 TOPS
Tensor INT8
238.1 TOPS
Ray
-
Ray
44.9 TOPS
Pixel Rate
380.2 GPixel/s
Pixel Rate
164.2 GPixel/s
Texture Rate
760.3 GTexel/s
Texture Rate
465.1 GTexel/s

Shaders
4,096 Shaders
Shaders
8,704 Shaders
TMUs
256 TMUs
TMUs
272 TMUs
ROPs
128 ROPs
ROPs
96 ROPs
Tensor Cores
128 T-Cores
Tensor Cores
272 T-Cores
RT Cores
64 RT-Cores
RT Cores
68 RT-Cores
CUs
64 CUs
SMs
68 SMs

Base Clock
2.4GHz
Base Clock
1.44GHz
Boost Clock
2.97GHz
Boost Clock
1.71GHz

L2 Cache
8.2MB shared
L2 Cache
5.1MB shared
L3 Cache
64MB shared
L3 Cache
-
L3 Bandwidth
2.25TB/s
L3 Bandwidth
-

16GB GDDR6
10GB GDDR6X
Memory Bus
256-bit
Memory Bus
320-bit
Memory Speed
20GT/s
Memory Speed
19GT/s
Memory Bandwidth
640GB/s
Memory Bandwidth
760.3GB/s

TDP
304W
TDP
320W
Max Temp
-
Max Temp
93°C Max

Multi-Monitor
3
Multi-Monitor
4
HDCP
HDCP 2.3
HDCP
HDCP 2.3

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

Encoder Model
VCN 4.0
Encoder Model
NVENC 7

Decoder Model
VCN 4.0
Decoder Model
NVDEC 5

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
2.5-Slots
PCIe
2-Slots
Height
111 mm (4.37")
Width
267 mm (10.51")
Depth
50 mm (1.97")
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
2x 8-Pin
Power Connectors
1x 12-Pin

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
Radeon 2023 branding
Branding
GeForce RTX 2018 branding
Codename
-
Codename
NV172
Chip Variant
Navi 48 XL
Chip Variant
GA102-200-KD-A1
Market Segment
Desktop
Market Segment
Desktop
Release Date
Jan 6, 2025
Release Date
Sep 17, 2020

Foundry
TSMC
Foundry
Samsung
Fabrication Node
N4P
Fabrication Node
8N
Die Size
357mm²
Die Size
628mm²
Transistor Count
53.9 Billion
Transistor Count
28.3 Billion
Transistor Density
151.2 MTr/mm²
Transistor Density
45.04 MTr/mm²

No images available
No images available