Apple 60-Core M2 Ultra vs NVIDIA GeForce RTX 4090 Full Specs

Summary

7,680 Shaders 1.4GHz	16,384 Shaders 2.52GHz
Shared Memory819.2GB/sLPDDR5	24GB GDDR6X1.01TB/s placeholder
Peak·FP32·FP16 21.47 TFLOPS	Peak·FP32·FP16 82.58 TFLOPS
Form Factor iGPU	Form Factor PCIe Card
TDP Shared	TDP 450W
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

Highlights

Peak OPS

Peak OPS FP32 FP16 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 Tensor INT4 Memory Bandwidth TDP

60-Core M2 Ultra21.47 TFLOPSFP16

x1

GeForce RTX 40902.64 POPSINT4 Tensor Sparse

x123.06

Show Top Score

Theoretical Performance

Clock Speed1398MHz UC·Boost·OC	Clock Speed2520MHz UC·Base·Boost·OC
Peak OPS 21.47 TFLOPSFP16	Peak OPS 2.64 POPSINT4 Tensor Sparse
-	Tensor FP8-16 660.6 TFLOPS FP8-16 Tensor Sparse 1.32 PFLOPS Tensor FP8-32 330.3 TFLOPS FP8-32 Tensor Sparse 660.6 TFLOPS
-	Tensor FP16-16 330.3 TFLOPS FP16-16 Tensor Sparse 660.6 TFLOPS Tensor FP16-32 165.2 TFLOPS FP16-32 Tensor Sparse 330.3 TFLOPS
-	BF16 82.58 TFLOPS Tensor BF16 165.2 TFLOPS BF16 Tensor Sparse 330.3 TFLOPS
Tensor TF32 -	Tensor TF32 82.58 TFLOPS
FP32 21.47 TFLOPS	FP32 82.58 TFLOPS
-	FP64 1.29 TFLOPS
Tensor INT4 -	Tensor INT4 1.32 POPS
-	Tensor INT8 660.6 TOPS
Ray -	Ray 190.9 TOPS
Pixel Rate 335.5 GPixel/s	Pixel Rate 443.5 GPixel/s
Texture Rate 671 GTexel/s	Texture Rate 1.29 TTexel/s

Core Config

Shaders 7,680 Shaders	Shaders 16,384 Shaders
TMUs 480 TMUs	TMUs 512 TMUs
ROPs 240 ROPs	ROPs 176 ROPs
Tensor Cores -	Tensor Cores 512 T-Cores
RT Cores -	RT Cores 128 RT-Cores
EUs 960 EUs	SMs 128 SMs

Clocks

Base Clock -	Base Clock 2.23GHz
Boost Clock 1.4GHz	Boost Clock 2.52GHz

Cache

L2 Cache 16.4MB shared

L2 Cache 73.7MB shared

Memory

Shared MemoryLPDDR5	24GB GDDR6X placeholder
Memory Bus 1024-bit	Memory Bus 384-bit
Memory Speed 6.4GT/s	Memory Speed 21GT/s
Memory Bandwidth 819.2GB/s	Memory Bandwidth 1.01TB/s

Power & Thermals

TDP Shared	TDP 450W
Max Temp -	Max Temp 90°C Max

Video Output

Multi-Monitor 8	Multi-Monitor 4
HDCP -	HDCP HDCP 2.3

Ports

-	3x DisplayPort 1.4
-	1x HDMI 2.1

Encoder

Encoder Model 4x Apple Media Engine 2

Encoder Model 2x NVENC 8

Decoder

Decoder Model 2x Apple Media Engine 2

Decoder Model NVDEC 5

Card

Form Factor iGPU	Form Factor PCIe Card
PCIe -	PCIe 3-Slots
-	Height 137 mm (5.39") Width 304 mm (11.97") Depth 61 mm (2.4")
Cooling Passive -	Cooling Open-Air 2x Fans
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

Chip

Manufacturer Apple	Manufacturer NVIDIA
Chip Designer Apple	Chip Designer NVIDIA
Architecture Apple Gen 5	Architecture Ada Lovelace
Family M Series	Family GeForce 40
Branding	Branding
Codename G14D	Codename NV182
Chip Variant -	Chip Variant AD102-200-A1
Market Segment Workstation	Market Segment Desktop
Release Date Jun 5, 2023	Release Date Oct 12, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node N5P	Fabrication Node 4N
Die Size 971mm²	Die Size 608mm²
Transistor Count 134 Billion	Transistor Count 76.3 Billion
Transistor Density 138 MTr/mm²	Transistor Density 125.4 MTr/mm²

Images

No images available

No images available

Used In

CPUs M2 Ultra (24C60G)	CPUs -
Desktops Mac Studio(M2 Ultra, Mid 2023)Mac Pro(M2 Ultra, Mid 2023)	Desktops OMEN 35L(Late 2024)OMEN 45L(Late 2024)Tinybox Green(Mid 2024)

Competitors

Apple60-Core M2 Ultra vs GPU Apple60-Core M3 Ultra Apple60-Core M2 Ultra vs GPU Apple80-Core M3 Ultra Apple60-Core M2 Ultra vs GPU NVIDIARTX PRO 4000 Blackwell SFF Show 11 more

NVIDIAGeForce RTX 4090 vs GPU NVIDIARTX PRO 5000 Blackwell NVIDIAGeForce RTX 4090 vs GPU NVIDIARTX PRO 4500 Blackwell NVIDIAGeForce RTX 4090 vs GPU AMDRadeon RX 9060 XT 16GB Show 5 more