GPUs

Apple Radeon Pro Vega 64X vs NVIDIA GeForce RTX 3060 Laptop 95W Full Specs

4,096 Shaders
1.47GHz
3,840 Shaders
1.57GHz
16GB HBM2512GB/s
6GB GDDR6336GB/s
··
12.03 TFLOPS
··
12.03 TFLOPS
Form Factor
Soldered
Form Factor
Soldered
TDP
125W
TDP
95W

Clock Speed
···
Clock Speed
···
Peak OPS
24.05 TFLOPSFP16
Peak OPS
385.1 TOPSINT4 Tensor Sparse
-
Tensor FP16-16
48.14 TFLOPS
FP16-16 Tensor Sparse
96.28 TFLOPS
Tensor FP16-32
24.07 TFLOPS
FP16-32 Tensor Sparse
48.14 TFLOPS
-
BF16
12.03 TFLOPS
Tensor BF16
24.07 TFLOPS
BF16 Tensor Sparse
48.14 TFLOPS
Tensor TF32
-
Tensor TF32
12.03 TFLOPS
FP32
12.03 TFLOPS
FP32
12.03 TFLOPS
FP64
751.6 GFLOPS
FP64
188 GFLOPS
Tensor INT4
-
Tensor INT4
192.6 TOPS
-
Tensor INT8
96.28 TOPS
Ray
-
Ray
18.15 TOPS
Pixel Rate
94 GPixel/s
Pixel Rate
75.2 GPixel/s
Texture Rate
375.8 GTexel/s
Texture Rate
188 GTexel/s

Shaders
4,096 Shaders
Shaders
3,840 Shaders
TMUs
256 TMUs
TMUs
120 TMUs
ROPs
64 ROPs
ROPs
48 ROPs
Tensor Cores
-
Tensor Cores
120 T-Cores
RT Cores
-
RT Cores
30 RT-Cores
CUs
64 CUs
SMs
30 SMs

Base Clock
1.25GHz
Base Clock
1.22GHz
Boost Clock
1.47GHz
Boost Clock
1.57GHz

L2 Cache
4MB shared
L2 Cache
3MB shared

16GB HBM2
6GB GDDR6
Memory Bus
2048-bit
Memory Bus
192-bit
Memory Speed
2GT/s
Memory Speed
14GT/s
Memory Bandwidth
512GB/s
Memory Bandwidth
336GB/s
ECC
No
ECC
No

TDP
125W
TDP
95W

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

Encoder Model
VCE 4.0
Encoder Model
NVENC 7
Codec
AVC (H.264)
HEVC (H.265)
Codec
AVC (H.264)
HEVC (H.265)

Decoder Model
UVD 7.0
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
Soldered
Form Factor
Soldered

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
Vega Pro branding
Branding
GeForce RTX 2018 branding
Codename
Greenland
Codename
NV176
Chip Variant
Vega 10 XL
Chip Variant
GA106-150-KA-A1
Market Segment
Laptop
Market Segment
Laptop
Release Date
Mar 19, 2019
Release Date
Feb 25, 2021

Foundry
GlobalFoundries
Foundry
Samsung
Fabrication Node
14LPP
Fabrication Node
8N
Die Size
486mm²
Die Size
276mm²
Transistor Count
12.5 Billion
Transistor Count
13.3 Billion
Transistor Density
25.72 MTr/mm²
Transistor Density
48.01 MTr/mm²