GPUs

Apple Radeon Pro Vega II Duo vs NVIDIA GeForce RTX 4070 Ti Super Full Specs

8,192 Shaders
1.72GHz
8,448 Shaders
2.61GHz
64GB HBM22.05TB/s
16GB GDDR6X716.8GB/s
··
28.18 TFLOPS
··
44.1 TFLOPS
Form Factor
MPX
Form Factor
PCIe Card
TDP
475W
TDP
285W
Power Connectors
-
Power Connectors
1x 16-Pin 12VHPWR

Clock Speed
··
Clock Speed
···
Peak OPS
56.36 TFLOPSFP16
Peak OPS
1.41 POPSINT4 Tensor Sparse
-
Tensor FP8-16
352.8 TFLOPS
FP8-16 Tensor Sparse
705.6 TFLOPS
Tensor FP8-32
176.4 TFLOPS
FP8-32 Tensor Sparse
352.8 TFLOPS
-
Tensor FP16-16
176.4 TFLOPS
FP16-16 Tensor Sparse
352.8 TFLOPS
Tensor FP16-32
88.2 TFLOPS
FP16-32 Tensor Sparse
176.4 TFLOPS
-
BF16
44.1 TFLOPS
Tensor BF16
88.2 TFLOPS
BF16 Tensor Sparse
176.4 TFLOPS
Tensor TF32
-
Tensor TF32
44.1 TFLOPS
FP32
28.18 TFLOPS
FP32
44.1 TFLOPS
FP64
7.04 TFLOPS
FP64
689 GFLOPS
Tensor INT4
-
Tensor INT4
705.6 TOPS
-
Tensor INT8
352.8 TOPS
Ray
-
Ray
101.9 TOPS
Pixel Rate
110.1 GPixel/s
Pixel Rate
292.3 GPixel/s
Texture Rate
440.3 GTexel/s
Texture Rate
689 GTexel/s

Shaders
8,192 Shaders
Shaders
8,448 Shaders
TMUs
512 TMUs
TMUs
264 TMUs
ROPs
128 ROPs
ROPs
112 ROPs
Tensor Cores
-
Tensor Cores
264 T-Cores
RT Cores
-
RT Cores
66 RT-Cores
CUs
128 CUs
SMs
66 SMs

Base Clock
-
Base Clock
2.34GHz
Boost Clock
1.72GHz
Boost Clock
2.61GHz

L2 Cache
4MB shared
L2 Cache
64MB shared

64GB HBM2
16GB GDDR6X
Memory Bus
4096-bit
Memory Bus
256-bit
Memory Speed
2GT/s
Memory Speed
22.4GT/s
Memory Bandwidth
2.05TB/s
Memory Bandwidth
716.8GB/s
ECC
No
ECC
No

TDP
475W
TDP
285W
Max Temp
-
Max Temp
90°C Max

Multi-Monitor
3
Multi-Monitor
4
HDCP
HDCP 2.2
HDCP
HDCP 2.3

-
1x HDMI 2.0
4x Thunderbolt 3
3x DisplayPort 1.4
1x HDMI 2.1
-

Encoder Model
VCE 4.1
Encoder Model
2x NVENC 8
Codec
AVC (H.264)
HEVC (H.265)
-
Codec
AVC (H.264)
HEVC (H.265)
AV1

Decoder Model
UVD 7.2
Decoder Model
NVDEC 5
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
-
-
AVC (H.264)
HEVC (H.265)
-
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
AVC (H.264)
HEVC (H.265)
AV1

Form Factor
MPX
Form Factor
PCIe Card
PCIe
4-Slots
PCIe
3-Slots
-
Height
137 mm (5.39")
Width
304 mm (11.97")
Depth
61 mm (2.4")
Cooling
Passive
-
Cooling
Open-Air
2x Fans
Power Connectors
-
Power Connectors
1x 16-Pin 12VHPWR

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
Vega Pro branding
Branding
GeForce RTX 2022 branding
Codename
Moonshot
Codename
NV183
Chip Variant
Vega 20 XT
Chip Variant
AD103-275-A1
Market Segment
Workstation
Market Segment
Desktop
Release Date
Dec 1, 2019
Release Date
Jan 8, 2024

Foundry
TSMC
Foundry
TSMC
Fabrication Node
N7
Fabrication Node
4N
Die Size
331mm²
Die Size
379mm²
Transistor Count
13.2 Billion
Transistor Count
45.9 Billion
Transistor Density
39.97 MTr/mm²
Transistor Density
121.2 MTr/mm²