Apple Radeon Pro 555X vs ZOTAC GeForce RTX 3070 Ti AMP Holo Full Specs

Summary

768 Shaders 907MHz	6,144 Shaders 1.83GHz
4GB GDDR594.4GB/s	8GB GDDR6X608.3GB/s
Peak·FP32·FP16 1.39 TFLOPS	Peak·FP32·FP16 22.49 TFLOPS
Form Factor Soldered	Form Factor PCIe Card
TDP 35W	TDP 310W
Power Connectors -	Power Connectors 2x 8-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 555X1.39 TFLOPSFP16

x1

GeForce RTX 3070 Ti AMP Holo719.6 TOPSINT4 Tensor Sparse

x516.52

Show Top Score

Theoretical Performance

Clock Speed907MHz UC·Boost·OC	Clock Speed1830MHz UC·Base·Boost·OC
Peak OPS 1.39 TFLOPSFP16	Peak OPS 719.6 TOPSINT4 Tensor Sparse
-	Tensor FP16-16 89.95 TFLOPS FP16-16 Tensor Sparse 179.9 TFLOPS Tensor FP16-32 44.97 TFLOPS FP16-32 Tensor Sparse 89.95 TFLOPS
-	BF16 22.49 TFLOPS Tensor BF16 44.97 TFLOPS BF16 Tensor Sparse 89.95 TFLOPS
Tensor TF32 -	Tensor TF32 22.49 TFLOPS
FP32 1.39 TFLOPS	FP32 22.49 TFLOPS
FP64 87.07 GFLOPS	FP64 351.4 GFLOPS
Tensor INT4 -	Tensor INT4 359.8 TOPS
-	Tensor INT8 179.9 TOPS
Ray -	Ray 33.92 TOPS
Pixel Rate 14.5 GPixel/s	Pixel Rate 175.7 GPixel/s
Texture Rate 43.5 GTexel/s	Texture Rate 351.4 GTexel/s

Core Config

Shaders 768 Shaders	Shaders 6,144 Shaders
TMUs 48 TMUs	TMUs 192 TMUs
ROPs 16 ROPs	ROPs 96 ROPs
Tensor Cores -	Tensor Cores 192 T-Cores
RT Cores -	RT Cores 48 RT-Cores
CUs 12 CUs	SMs 48 SMs

Clocks

Base Clock -	Base Clock 1.57GHz
Boost Clock 907MHz	Boost Clock 1.83GHz

Cache

L2 Cache 1MB shared

L2 Cache 4.1MB shared

Memory

4GB GDDR5	8GB GDDR6X
Memory Bus 128-bit	Memory Bus 256-bit
Memory Speed 5.9GT/s	Memory Speed 19GT/s
Memory Bandwidth 94.4GB/s	Memory Bandwidth 608.3GB/s

Power & Thermals

TDP 35W	TDP 310W
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 3.4

Encoder Model NVENC 7

Decoder

Decoder Model UVD 6.3

Decoder Model NVDEC 5

Card

Form Factor Soldered	Form Factor PCIe Card
PCIe -	PCIe 3.2-Slots
-	Height 131.8 mm (5.19") Width 317.8 mm (12.51") Depth 64.6 mm (2.54")
Cooling Open-Air -	Cooling Open-Air 3x Fans
Power Connectors -	Power Connectors 2x 8-Pin

Chip

Manufacturer Apple	Manufacturer ZOTAC
Chip Designer AMD	Chip Designer NVIDIA
Architecture GCN 4	Architecture Ampere
Family Radeon Pro	Family GeForce 30
Branding	Branding
Codename Baffin	Codename NV174
Chip Variant Polaris 21 XL	Chip Variant GA104-150-A1
Market Segment Laptop	Market Segment Desktop
Release Date Jul 16, 2018	Release Date Jun 10, 2021

Fabrication

Foundry GlobalFoundries	Foundry Samsung
Fabrication Node 14LPP	Fabrication Node 8N
Die Size 123mm²	Die Size 393mm²
Transistor Count 3 Billion	Transistor Count 17.4 Billion
Transistor Density 24.39 MTr/mm²	Transistor Density 44.33 MTr/mm²

Images

No images available

No images available

Used In

Laptops MacBook Pro 15(Mid 2018)MacBook Pro 15(Mid 2019)	Laptops -
All-in-Ones iMac 21.5(Early 2019)	All-in-Ones -

Competitors

AppleRadeon Pro 555X vs GPU NVIDIAGeForce RTX 5050 Laptop 50W AppleRadeon Pro 555X vs GPU NVIDIAGeForce RTX 5050 Laptop 60W AppleRadeon Pro 555X vs GPU NVIDIAGeForce RTX 5050 Laptop 80W Show 12 more

ZOTACGeForce RTX 3070 Ti AMP Holo vs GPU NVIDIAGeForce RTX 5070 ZOTACGeForce RTX 3070 Ti AMP Holo vs GPU AMDRadeon RX 9070 XT ZOTACGeForce RTX 3070 Ti AMP Holo vs GPU NVIDIAGeForce RTX 5070 Ti Show 12 more