Apple Radeon Pro 570X vs NVIDIA GeForce RTX 3060 Full Specs

Summary

1,792 Shaders 1.1GHz	3,584 Shaders 1.78GHz
4GB GDDR5217.6GB/s	12GB GDDR6360GB/s
Peak·FP32·FP16 3.96 TFLOPS	Peak·FP32·FP16 12.74 TFLOPS
Form Factor Soldered	Form Factor PCIe Card
TDP 95W	TDP 170W
Power Connectors -	Power Connectors 1x 12-Pin

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

Radeon Pro 570X3.96 TFLOPSFP16

x1

GeForce RTX 3060407.6 TOPSINT4 Tensor Sparse

x102.92

Show Top Score

Theoretical Performance

Clock Speed1105MHz UC·Base·Boost·OC	Clock Speed1777MHz UC·Base·Boost·OC
Peak OPS 3.96 TFLOPSFP16	Peak OPS 407.6 TOPSINT4 Tensor Sparse
-	Tensor FP16-16 50.95 TFLOPS FP16-16 Tensor Sparse 101.9 TFLOPS Tensor FP16-32 25.48 TFLOPS FP16-32 Tensor Sparse 50.95 TFLOPS
-	BF16 12.74 TFLOPS Tensor BF16 25.48 TFLOPS BF16 Tensor Sparse 50.95 TFLOPS
Tensor TF32 -	Tensor TF32 12.74 TFLOPS
FP32 3.96 TFLOPS	FP32 12.74 TFLOPS
FP64 247.5 GFLOPS	FP64 199 GFLOPS
Tensor INT4 -	Tensor INT4 203.8 TOPS
-	Tensor INT8 101.9 TOPS
Ray -	Ray 19.21 TOPS
Pixel Rate 35.4 GPixel/s	Pixel Rate 85.3 GPixel/s
Texture Rate 123.8 GTexel/s	Texture Rate 199 GTexel/s

Core Config

Shaders 1,792 Shaders	Shaders 3,584 Shaders
TMUs 112 TMUs	TMUs 112 TMUs
ROPs 32 ROPs	ROPs 48 ROPs
Tensor Cores -	Tensor Cores 112 T-Cores
RT Cores -	RT Cores 28 RT-Cores
CUs 28 CUs	SMs 28 SMs

Clocks

Base Clock 1GHz	Base Clock 1.32GHz
Boost Clock 1.1GHz	Boost Clock 1.78GHz

Cache

L2 Cache 2MB shared

L2 Cache 3.1MB shared

Memory

4GB GDDR5	12GB GDDR6
Memory Bus 256-bit	Memory Bus 192-bit
Memory Speed 6.8GT/s	Memory Speed 15GT/s
Memory Bandwidth 217.6GB/s	Memory Bandwidth 360GB/s
ECC No	ECC No

Power & Thermals

TDP 95W	TDP 170W
Max Temp -	Max Temp 93°C Max

Video Output

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

Ports

-	3x DisplayPort 1.4
-	1x HDMI 2.1

Encoder

Encoder Model VCE 3.0

Encoder Model NVENC 7

Decoder

Decoder Model UVD 6.3

Decoder Model NVDEC 5

Card

Form Factor Soldered	Form Factor PCIe Card
PCIe -	PCIe 1.9-Slots
-	Height 112 mm (4.41") Width 242 mm (9.53") Depth 38 mm (1.5")
Cooling Open-Air -	Cooling Open-Air 2x Fans
Power Connectors -	Power Connectors 1x 12-Pin

Chip

Manufacturer Apple	Manufacturer NVIDIA
Chip Designer AMD	Chip Designer NVIDIA
Architecture GCN 4	Architecture Ampere
Family Radeon Pro	Family GeForce 30
Branding	Branding
Codename Ellesmere	Codename NV176
Chip Variant Polaris 20 XL	Chip Variant GA106-150-KA-A1
Market Segment Laptop	Market Segment Desktop
Release Date Mar 18, 2019	Release Date Feb 25, 2021

Fabrication

Foundry GlobalFoundries	Foundry Samsung
Fabrication Node 14LPP	Fabrication Node 8N
Die Size 232mm²	Die Size 276mm²
Transistor Count 5.7 Billion	Transistor Count 13.3 Billion
Transistor Density 24.57 MTr/mm²	Transistor Density 48.01 MTr/mm²

Images

No images available

No images available

Used In

Desktops -	Desktops XPS(XD8950, Late 2021)Aurora(R13, Late 2021)Aurora(R14, Late 2021) Show 10 more
All-in-Ones iMac 27(Early 2019)	All-in-Ones Surface Studio 2+(Late 2022)

Competitors

AppleRadeon Pro 570X vs GPU NVIDIAGeForce RTX 5050 Laptop 60W AppleRadeon Pro 570X vs GPU NVIDIAGeForce RTX 5050 Laptop 100W AppleRadeon Pro 570X vs GPU NVIDIAGeForce RTX 5050 Laptop 50W Show 12 more

NVIDIAGeForce RTX 3060 vs GPU AMDRadeon RX 7400 NVIDIAGeForce RTX 3060 vs GPU AMDRadeon RX 9060 NVIDIAGeForce RTX 3060 vs GPU AMDRadeon RX 9060 XT Show 12 more