GPUs

NVIDIA GeForce RTX 4090 D vs AMD Radeon RX 9070 XT Full Specs

14,592 Shaders
2.52GHz
4,096 Shaders
2.97GHz
24GB GDDR6X1.01TB/s
16GB GDDR6640GB/s
··
73.54 TFLOPS
··
48.66 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
450W
TDP
304W
Power Connectors
1x 16-Pin 12VHPWR
-
Power Connectors
-
2x 8-Pin

GeForce RTX 4090 DGeForce RTX 4090 D2.35 POPSINT4 Tensor Sparse
x1.51
Radeon RX 9070 XTRadeon RX 9070 XT1.56 POPSINT4 Tensor Sparse
x1

Clock Speed
···
Clock Speed
···
Peak OPS
2.35 POPSINT4 Tensor Sparse
Peak OPS
1.56 POPSINT4 Tensor Sparse
Tensor FP8-16
588.3 TFLOPS
FP8-16 Tensor Sparse
1.18 PFLOPS
Tensor FP8-32
294.2 TFLOPS
FP8-32 Tensor Sparse
588.3 TFLOPS
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
294.2 TFLOPS
FP16-16 Tensor Sparse
588.3 TFLOPS
Tensor FP16-32
147.1 TFLOPS
FP16-32 Tensor Sparse
294.2 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
BF16
73.54 TFLOPS
Tensor BF16
147.1 TFLOPS
BF16 Tensor Sparse
294.2 TFLOPS
BF16
97.32 TFLOPS
Tensor BF16
97.32 TFLOPS
BF16 Tensor Sparse
194.6 TFLOPS
Tensor TF32
73.54 TFLOPS
Tensor TF32
-
FP32
73.54 TFLOPS
FP32
48.66 TFLOPS
FP64
1.15 TFLOPS
FP64
1.52 TFLOPS
Tensor INT4
1.18 POPS
Tensor INT4
778.6 TOPS
Tensor INT8
588.3 TOPS
Tensor INT8
389.3 TOPS
Ray
170 TOPS
Ray
-
Pixel Rate
443.5 GPixel/s
Pixel Rate
380.2 GPixel/s
Texture Rate
1.15 TTexel/s
Texture Rate
760.3 GTexel/s

Shaders
14,592 Shaders
Shaders
4,096 Shaders
TMUs
456 TMUs
TMUs
256 TMUs
ROPs
176 ROPs
ROPs
128 ROPs
Tensor Cores
456 T-Cores
Tensor Cores
128 T-Cores
RT Cores
114 RT-Cores
RT Cores
64 RT-Cores
SMs
114 SMs
CUs
64 CUs

Base Clock
2.23GHz
Base Clock
2.4GHz
Boost Clock
2.52GHz
Boost Clock
2.97GHz

L2 Cache
73.7MB shared
L2 Cache
8.2MB shared
L3 Cache
-
L3 Cache
64MB shared
L3 Bandwidth
-
L3 Bandwidth
2.25TB/s

24GB GDDR6X
16GB GDDR6
Memory Bus
384-bit
Memory Bus
256-bit
Memory Speed
21GT/s
Memory Speed
20GT/s
Memory Bandwidth
1.01TB/s
Memory Bandwidth
640GB/s
ECC
No
ECC
No

TDP
450W
TDP
304W
Max Temp
90°C Max
Max Temp
-

Multi-Monitor
4
Multi-Monitor
3
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
2x NVENC 8
Encoder Model
VCN 4.0

Decoder Model
NVDEC 5
Decoder Model
VCN 4.0

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
3-Slots
PCIe
2.5-Slots
Height
137 mm (5.39")
Width
304 mm (11.97")
Depth
61 mm (2.4")
Height
111 mm (4.37")
Width
267 mm (10.51")
Depth
50 mm (1.97")
Cooling
Open-Air
2x Fans
Cooling
Open-Air
3x Fans
Power Connectors
1x 16-Pin 12VHPWR
Power Connectors
2x 8-Pin

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
GeForce RTX 2022 branding
Branding
Radeon 2023 branding
Codename
NV182
Codename
-
Chip Variant
AD102-200-A1
Chip Variant
Navi 48 XL
Market Segment
Desktop
Market Segment
Desktop
Release Date
Dec 28, 2023
Release Date
Jan 6, 2025

Foundry
TSMC
Foundry
TSMC
Fabrication Node
4N
Fabrication Node
N4P
Die Size
608mm²
Die Size
357mm²
Transistor Count
76.3 Billion
Transistor Count
53.9 Billion
Transistor Density
125.4 MTr/mm²
Transistor Density
151.2 MTr/mm²

No images available
No images available