Apple Radeon Pro Vega 64X vs NVIDIA GeForce RTX 5070 Laptop 50W Full Specs

Summary

4,096 Shaders 1.47GHz	4,608 Shaders 1.43GHz
16GB HBM2512GB/s	8GB GDDR7448GB/s
Peak·FP32·FP16 12.03 TFLOPS	Peak·FP32·FP16 13.13 TFLOPS
Form Factor Soldered	Form Factor Soldered
TDP 125W	TDP 50W

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP4 FP4 Tensor Sparse Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse 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 Memory Bandwidth TDP

Radeon Pro Vega 64X24.05 TFLOPSFP16

x1

GeForce RTX 5070 Laptop 50W665 TFLOPSFP4 Tensor Sparse

x27.65

Show Top Score

Theoretical Performance

Clock Speed1468MHz UC·Base·Boost·OC	Clock Speed1425MHz UC·Base·Boost·OC
Peak OPS 24.05 TFLOPSFP16	Peak OPS 665 TFLOPSFP4 Tensor Sparse
-	Tensor FP4 332.5 TFLOPS FP4 Tensor Sparse 665 TFLOPS
-	Tensor FP8-16 166.3 TFLOPS FP8-16 Tensor Sparse 332.5 TFLOPS Tensor FP8-32 83.13 TFLOPS FP8-32 Tensor Sparse 166.3 TFLOPS
-	Tensor FP16-16 83.13 TFLOPS FP16-16 Tensor Sparse 166.3 TFLOPS Tensor FP16-32 41.56 TFLOPS FP16-32 Tensor Sparse 83.13 TFLOPS
-	BF16 13.13 TFLOPS Tensor BF16 41.56 TFLOPS BF16 Tensor Sparse 83.13 TFLOPS
Tensor TF32 -	Tensor TF32 20.78 TFLOPS
FP32 12.03 TFLOPS	FP32 13.13 TFLOPS
FP64 751.6 GFLOPS	FP64 205.2 GFLOPS
-	Tensor INT8 166.3 TOPS
Ray -	Ray 39.83 TOPS
Pixel Rate 94 GPixel/s	Pixel Rate 68.4 GPixel/s
Texture Rate 375.8 GTexel/s	Texture Rate 205.2 GTexel/s

Core Config

Shaders 4,096 Shaders	Shaders 4,608 Shaders
TMUs 256 TMUs	TMUs 144 TMUs
ROPs 64 ROPs	ROPs 48 ROPs
Tensor Cores -	Tensor Cores 144 T-Cores
RT Cores -	RT Cores 36 RT-Cores
CUs 64 CUs	SMs 36 SMs

Clocks

Base Clock 1.25GHz	Base Clock 1.4GHz
Boost Clock 1.47GHz	Boost Clock 1.43GHz
Tensor Clock -	Tensor Clock 2.25GHz

Cache

L2 Cache 4.1MB shared

L2 Cache 32.8MB shared

Memory

16GB HBM2	8GB GDDR7
Memory Bus 2048-bit	Memory Bus 128-bit
Memory Speed 2GT/s	Memory Speed 28GT/s
Memory Bandwidth 512GB/s	Memory Bandwidth 448GB/s
ECC No	ECC No

Power & Thermals

TDP 125W

TDP 50W

Video Output

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

Encoder

Encoder Model VCE 4.0

Encoder Model NVENC 9

Decoder

Decoder Model UVD 7.0

Decoder Model NVDEC 6

Card

Form Factor Soldered

Form Factor Soldered

Chip

Manufacturer Apple	Manufacturer NVIDIA
Chip Designer AMD	Chip Designer NVIDIA
Architecture GCN 5	Architecture Blackwell
Family Radeon Pro Vega	Family GeForce 50
Branding	Branding
Codename Greenland	Codename NV196
Chip Variant Vega 10 XL	Chip Variant -
Market Segment Laptop	Market Segment Laptop
Release Date Mar 19, 2019	Release Date Jan 6, 2025

Fabrication

Foundry GlobalFoundries	Foundry TSMC
Fabrication Node 14LPP	Fabrication Node 4NP
Die Size 486mm²	Die Size 183mm²
Transistor Count 12.5 Billion	Transistor Count 23 Billion
Transistor Density 25.72 MTr/mm²	Transistor Density 125.7 MTr/mm²

Images

No images available

No images available

Used In

All-in-Ones iMac Pro(Late 2017)

All-in-Ones -

Competitors

AppleRadeon Pro Vega 64X vs GPU NVIDIAGeForce RTX 5060 Laptop 80W AppleRadeon Pro Vega 64X vs GPU NVIDIAGeForce RTX 5070 Laptop 80W AppleRadeon Pro Vega 64X vs GPU NVIDIAGeForce RTX 5060 Laptop 50W Show 12 more

NVIDIAGeForce RTX 5070 Laptop 50W vs GPU NVIDIAGeForce RTX 5060 Laptop 80W NVIDIAGeForce RTX 5070 Laptop 50W vs GPU NVIDIAGeForce RTX 5060 Laptop 50W NVIDIAGeForce RTX 5070 Laptop 50W vs GPU NVIDIAGeForce RTX 5060 Laptop 60W Show 12 more