Apple 80-Core M3 Ultra vs NVIDIA RTX PRO 4000 Blackwell SFF Full Specs

Summary

10,240 Shaders 1.38GHz	8,960 Shaders 1.34GHz
Shared Memory819.2GB/sLPDDR5	24GB GDDR7432GB/s placeholder
Peak·FP32·FP16 28.26 TFLOPS	Peak·FP32·FP16 23.96 TFLOPS
Form Factor iGPU	Form Factor PCIe Card
TDP Shared	TDP 70W

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

80-Core M3 Ultra28.26 TFLOPSFP16

x1

RTX PRO 4000 Blackwell SFF766.7 TFLOPSFP4 Tensor Sparse

x27.13

Show Top Score

Theoretical Performance

Clock Speed1380MHz UC·Boost·OC	Clock Speed1337MHz UC·Base·Boost·OC
Peak OPS 28.26 TFLOPSFP16	Peak OPS 766.7 TFLOPSFP4 Tensor Sparse
-	Tensor FP4 383.3 TFLOPS FP4 Tensor Sparse 766.7 TFLOPS
-	Tensor FP8-16 191.7 TFLOPS FP8-16 Tensor Sparse 383.3 TFLOPS Tensor FP8-32 95.84 TFLOPS FP8-32 Tensor Sparse 191.7 TFLOPS
-	Tensor FP16-16 95.84 TFLOPS FP16-16 Tensor Sparse 191.7 TFLOPS Tensor FP16-32 47.92 TFLOPS FP16-32 Tensor Sparse 95.84 TFLOPS
-	BF16 23.96 TFLOPS Tensor BF16 47.92 TFLOPS BF16 Tensor Sparse 95.84 TFLOPS
Tensor TF32 -	Tensor TF32 23.96 TFLOPS
FP32 28.26 TFLOPS	FP32 23.96 TFLOPS
-	FP64 374.4 GFLOPS
-	Tensor INT8 191.7 TOPS
Ray -	Ray 72.66 TOPS
Pixel Rate 441.6 GPixel/s	Pixel Rate 128.4 GPixel/s
Texture Rate 883.2 GTexel/s	Texture Rate 374.4 GTexel/s

Core Config

Shaders 10,240 Shaders	Shaders 8,960 Shaders
TMUs 640 TMUs	TMUs 280 TMUs
ROPs 320 ROPs	ROPs 96 ROPs
Tensor Cores -	Tensor Cores 280 T-Cores
RT Cores 80 RT-Cores	RT Cores 70 RT-Cores
EUs 1,280 EUs	SMs 70 SMs

Clocks

Base Clock -	Base Clock 790MHz
Boost Clock 1.38GHz	Boost Clock 1.34GHz

Cache

L2 Cache 16.4MB shared

L2 Cache 49.1MB shared

Memory

Shared MemoryLPDDR5	24GB GDDR7 placeholder
Memory Bus 1024-bit	Memory Bus 192-bit
Memory Speed 6.4GT/s	Memory Speed 18GT/s
Memory Bandwidth 819.2GB/s	Memory Bandwidth 432GB/s
ECC -	ECC Yes

Power & Thermals

TDP Shared

TDP 70W

Video Output

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

Ports

-	4x DisplayPort 2.1

Encoder

Encoder Model 4x Apple Media Engine 3

Encoder Model 2x NVENC 9

Decoder

Decoder Model 2x Apple Media Engine 3

Decoder Model 2x NVDEC 6

Card

Form Factor iGPU	Form Factor PCIe Card
PCIe -	PCIe 1-Slots
-	Height 69 mm (2.72") Width 167 mm (6.58") Depth 20 mm (0.79")
Cooling Passive -	Cooling Blower 1x Fan

Chip

Manufacturer Apple	Manufacturer NVIDIA
Chip Designer Apple	Chip Designer NVIDIA
Architecture Apple Gen 6	Architecture Blackwell
Family M Series	Family RTX PRO Blackwell
Branding	Branding
Codename G15D	Codename NV193
Chip Variant -	Chip Variant GB203-200-A1
Market Segment Workstation	Market Segment Workstation
Release Date Mar 5, 2025	Release Date Aug 11, 2025

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node N3B	Fabrication Node 4NP
Die Size 954mm²	Die Size 378mm²
Transistor Count 184 Billion	Transistor Count 45.6 Billion
Transistor Density 193 MTr/mm²	Transistor Density 120.6 MTr/mm²

Images

No images available

No images available

Used In

CPUs M3 Ultra (32C80G)	CPUs -
Desktops Mac Studio(M3 Ultra, Early 2025)	Desktops -

Competitors

Apple80-Core M3 Ultra vs GPU Apple60-Core M3 Ultra Apple80-Core M3 Ultra vs GPU NVIDIARTX PRO 4000 Blackwell Apple80-Core M3 Ultra vs GPU NVIDIARTX PRO 4500 Blackwell Show 12 more

NVIDIARTX PRO 4000 Blackwell SFF vs GPU NVIDIARTX PRO 4000 Blackwell NVIDIARTX PRO 4000 Blackwell SFF vs GPU NVIDIARTX PRO 2000 Blackwell NVIDIARTX PRO 4000 Blackwell SFF vs GPU NVIDIARTX PRO 4500 Blackwell Show 12 more