NVIDIA GeForce RTX 3050 vs Apple 60-Core M2 Ultra Full Specs

Summary

2,560 Shaders 1.78GHz	7,680 Shaders 1.4GHz
8GB GDDR6224GB/s placeholder	Shared Memory819.2GB/sLPDDR5
Peak·FP32·FP16 9.1 TFLOPS	Peak·FP32·FP16 21.47 TFLOPS
Form Factor PCIe Card	Form Factor iGPU
TDP 115W	TDP Shared
Power Connectors 1x 12-Pin	Power Connectors -

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

GeForce RTX 3050291.1 TOPSINT4 Tensor Sparse

x13.56

60-Core M2 Ultra21.47 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed1777MHz UC·Base·Boost·OC	Clock Speed1398MHz UC·Boost·OC
Peak OPS 291.1 TOPSINT4 Tensor Sparse	Peak OPS 21.47 TFLOPSFP16
Tensor FP16-16 36.39 TFLOPS FP16-16 Tensor Sparse 72.79 TFLOPS Tensor FP16-32 18.2 TFLOPS FP16-32 Tensor Sparse 36.39 TFLOPS	-
BF16 9.1 TFLOPS Tensor BF16 18.2 TFLOPS BF16 Tensor Sparse 36.39 TFLOPS	-
Tensor TF32 9.1 TFLOPS	Tensor TF32 -
FP32 9.1 TFLOPS	FP32 21.47 TFLOPS
FP64 142.2 GFLOPS	-
Tensor INT4 145.6 TOPS	Tensor INT4 -
Tensor INT8 72.79 TOPS	-
Ray 13.72 TOPS	Ray -
Pixel Rate 56.9 GPixel/s	Pixel Rate 335.5 GPixel/s
Texture Rate 142.2 GTexel/s	Texture Rate 671 GTexel/s

Core Config

Shaders 2,560 Shaders	Shaders 7,680 Shaders
TMUs 80 TMUs	TMUs 480 TMUs
ROPs 32 ROPs	ROPs 240 ROPs
Tensor Cores 80 T-Cores	Tensor Cores -
RT Cores 20 RT-Cores	RT Cores -
SMs 20 SMs	EUs 960 EUs

Clocks

Base Clock 1.55GHz	Base Clock -
Boost Clock 1.78GHz	Boost Clock 1.4GHz

Cache

L2 Cache 2MB shared

L2 Cache 16.4MB shared

Memory

8GB GDDR6 placeholder	Shared MemoryLPDDR5
Memory Bus 128-bit	Memory Bus 1024-bit
Memory Speed 14GT/s	Memory Speed 6.4GT/s
Memory Bandwidth 224GB/s	Memory Bandwidth 819.2GB/s
ECC No	ECC No

Power & Thermals

TDP 115W

TDP Shared

Video Output

Multi-Monitor 3	Multi-Monitor 8
HDCP HDCP 2.3	HDCP -

Ports

3x DisplayPort 1.4	-
1x HDMI 2.1	-

Encoder

Encoder Model NVENC 7

Encoder Model 4x Apple Media Engine 2

Decoder

Decoder Model NVDEC 5

Decoder Model 2x Apple Media Engine 2

Card

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

Chip

Manufacturer NVIDIA	Manufacturer Apple
Chip Designer NVIDIA	Chip Designer Apple
Architecture Ampere	Architecture Apple Gen 5
Family GeForce 30	Family M Series
Branding	Branding
Codename NV177	Codename G14D
Chip Variant GA107-140-A1	Chip Variant -
Market Segment Desktop	Market Segment Workstation
Release Date Dec 16, 2022	Release Date Jun 5, 2023

Fabrication

Foundry Samsung	Foundry TSMC
Fabrication Node 8N	Fabrication Node N5P
Die Size 200mm²	Die Size 971mm²
Transistor Count 8.7 Billion	Transistor Count 134 Billion
Transistor Density 43.5 MTr/mm²	Transistor Density 138 MTr/mm²

Images

No images available

No images available

Used In

CPUs -	CPUs M2 Ultra (24C60G)
Desktops Aurora(R13, Late 2021)Aurora(R14, Late 2021)Envy(Early 2022) Show 3 more	Desktops Mac Studio(M2 Ultra, Mid 2023)Mac Pro(M2 Ultra, Mid 2023)

Competitors

NVIDIAGeForce RTX 3050 vs GPU AMDRadeon RX 7400 NVIDIAGeForce RTX 3050 vs GPU AMDRadeon RX 7650 GRE NVIDIAGeForce RTX 3050 vs GPU AMDRadeon RX 9060 XT Show 10 more

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 12 more