NVIDIA V100 SXM vs Apple 32-Core M5 Max Full Specs

Summary

5,120 Shaders 1.53GHz	4,096 Shaders 1.62GHz
32GB HBM2896GB/s placeholder	Shared Memory460.8GB/sLPDDR5X
Peak·FP32·FP16 15.67 TFLOPS	Peak·FP32·FP16 13.27 TFLOPS
Form Factor SXM3	Form Factor iGPU
TDP 300W	TDP Shared

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP8-16 Tensor FP8-32 Tensor FP16-16 Tensor FP16-32 FP64 Memory Bandwidth TDP

V100 SXM125.3 TFLOPSFP16-16 Tensor

x4.72

32-Core M5 Max26.54 TFLOPSFP8-16 Tensor

x1

Show Top Score

Theoretical Performance

Clock Speed1530MHz UC·Base·Boost·OC	Clock Speed1620MHz UC·Boost·OC
Peak OPS 125.3 TFLOPSFP16-16 Tensor	Peak OPS 26.54 TFLOPSFP8-16 Tensor
-	Tensor FP8-16 26.54 TFLOPS Tensor FP8-32 26.54 TFLOPS
Tensor FP16-16 125.3 TFLOPS Tensor FP16-32 125.3 TFLOPS	Tensor FP16-16 13.27 TFLOPS Tensor FP16-32 13.27 TFLOPS
FP32 15.67 TFLOPS	FP32 13.27 TFLOPS
FP64 7.83 TFLOPS	-
Pixel Rate 195.8 GPixel/s	Pixel Rate 207.4 GPixel/s
Texture Rate 489.6 GTexel/s	Texture Rate 414.7 GTexel/s

Core Config

Shaders 5,120 Shaders	Shaders 4,096 Shaders
TMUs 320 TMUs	TMUs 256 TMUs
ROPs 128 ROPs	ROPs 128 ROPs
Tensor Cores 640 T-Cores	Tensor Cores 32 T-Cores
RT Cores -	RT Cores 32 RT-Cores
SMs 80 SMs	EUs 512 EUs

Clocks

Base Clock 1.29GHz	Base Clock -
Boost Clock 1.53GHz	Boost Clock 1.62GHz

Cache

L2 Cache 6.1MB shared

L2 Cache 8.2MB shared

Memory

32GB HBM2 placeholder	Shared MemoryLPDDR5X
Memory Bus 4096-bit	Memory Bus 384-bit
Memory Speed 1.8GT/s	Memory Speed 9.6GT/s
Memory Bandwidth 896GB/s	Memory Bandwidth 460.8GB/s
ECC No	ECC No

Power & Thermals

TDP 300W

TDP Shared

Video Output

Multi-Monitor -

Multi-Monitor 4

Encoder

Encoder Model 3x NVENC 5

Encoder Model 2x Apple Media Engine 3

Decoder

Decoder Model NVDEC 3

Decoder Model 2x Apple Media Engine 3

Card

Form Factor SXM3	Form Factor iGPU
Cooling Passive	Cooling Open-Air

Chip

Manufacturer NVIDIA	Manufacturer Apple
Chip Designer NVIDIA	Chip Designer Apple
Architecture Volta	Architecture Apple Gen 8
Family Server	Family M Series
Branding	Branding
Codename NV140	Codename G17M
Chip Variant GV100-400-A1	Chip Variant -
Market Segment Server	Market Segment Desktop
Release Date Mar 27, 2018	Release Date Mar 3, 2026

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 12FFN	Fabrication Node N3P
Die Size 815mm²	Die Size -
Transistor Count 21.1 Billion	Transistor Count -
Transistor Density 25.89 MTr/mm²	Transistor Density -

Images

No images available

No images available

Used In

CPUs -	CPUs M5 Max (18C32G)
Laptops -	Laptops MacBook Pro 14(M5 Max, Early 2026)MacBook Pro 16(M5 Max, Early 2026)

Competitors

NVIDIAV100 SXM vs GPU AMDRadeon RX 9070 XT NVIDIAV100 SXM vs GPU NVIDIAGeForce RTX 5070 NVIDIAV100 SXM vs GPU Apple40-Core M5 Max Show 2 more

Apple32-Core M5 Max vs GPU Apple40-Core M5 Max Apple32-Core M5 Max vs GPU Apple20-Core M5 Pro Apple32-Core M5 Max vs GPU Apple60-Core M3 Ultra Show 12 more