Apple 48-Core M1 Ultra vs NVIDIA GB10 Full Specs

Summary

6,144 Shaders 1.3GHz	6,144 Shaders 2.52GHz
Shared Memory819.2GB/sLPDDR5	Shared Memory273.1GB/sLPDDR5X
Peak·FP32·FP16 15.93 TFLOPS	Peak·FP32·FP16 31.03 TFLOPS
Form Factor iGPU	Form Factor iGPU
TDP Shared	TDP Shared

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

48-Core M1 Ultra15.93 TFLOPSFP16

x1

GB10992.9 TFLOPSFP4 Tensor Sparse

x62.35

Show Top Score

Theoretical Performance

Clock Speed1296MHz UC·Boost·OC	Clock Speed2525MHz UC·Base·Boost·OC
Peak OPS 15.93 TFLOPSFP16	Peak OPS 992.9 TFLOPSFP4 Tensor Sparse
-	Tensor FP4 496.4 TFLOPS FP4 Tensor Sparse 992.9 TFLOPS
-	Tensor FP8-16 248.2 TFLOPS FP8-16 Tensor Sparse 496.4 TFLOPS Tensor FP8-32 124.1 TFLOPS FP8-32 Tensor Sparse 248.2 TFLOPS
-	Tensor FP16-16 124.1 TFLOPS FP16-16 Tensor Sparse 248.2 TFLOPS Tensor FP16-32 62.05 TFLOPS FP16-32 Tensor Sparse 124.1 TFLOPS
-	BF16 62.05 TFLOPS Tensor BF16 62.05 TFLOPS BF16 Tensor Sparse 124.1 TFLOPS
Tensor TF32 -	Tensor TF32 31.03 TFLOPS
FP32 15.93 TFLOPS	FP32 31.03 TFLOPS
-	FP64 15.51 TFLOPS
-	Tensor INT8 248.2 TOPS
Ray -	Ray 94.1 TOPS
Pixel Rate 248.8 GPixel/s	Pixel Rate 80.8 GPixel/s
Texture Rate 497.7 GTexel/s	Texture Rate 484.8 GTexel/s

Core Config

Shaders 6,144 Shaders	Shaders 6,144 Shaders
TMUs 384 TMUs	TMUs 192 TMUs
ROPs 192 ROPs	ROPs 32 ROPs
Tensor Cores -	Tensor Cores 192 T-Cores
RT Cores -	RT Cores 48 RT-Cores
EUs 768 EUs	SMs 48 SMs

Clocks

Base Clock -	Base Clock 2.42GHz
Boost Clock 1.3GHz	Boost Clock 2.52GHz

Cache

L2 Cache 8.2MB shared

L2 Cache 24.6MB shared

Memory

Shared MemoryLPDDR5	Shared MemoryLPDDR5X
Memory Bus 1024-bit	Memory Bus 256-bit
Memory Speed 6.4GT/s	Memory Speed 8.5GT/s
Memory Bandwidth 819.2GB/s	Memory Bandwidth 273.1GB/s
ECC No	ECC No

Video Output

Multi-Monitor 5	Multi-Monitor 4
HDCP -	HDCP HDCP 2.3

Encoder

Encoder Model 4x Apple Media Engine 2

Encoder Model NVENC 9

Decoder

Decoder Model 2x Apple Media Engine 2

Decoder Model NVDEC 6

Card

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

Chip

Manufacturer Apple	Manufacturer NVIDIA
Chip Designer Apple	Chip Designer NVIDIA
Architecture Apple Gen 4	Architecture Blackwell
Family M Series	Family -
Branding	Branding
Codename G13D	Codename Thor
Market Segment Workstation	Market Segment Embedded
Release Date Mar 8, 2022	Release Date Jan 6, 2025

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node N5	Fabrication Node N3E
Die Size 865mm²	Die Size -
Transistor Count 114 Billion	Transistor Count -
Transistor Density 132 MTr/mm²	Transistor Density -

Images

No images available

No images available

Used In

CPUs M1 Ultra (20C48G)	CPUs Grace Blackwell GB10
Desktops Mac Studio(M1 Ultra, Early 2022)	Desktops DGX Spark(Late 2025)

Competitors

Apple48-Core M1 Ultra vs GPU Apple60-Core M3 Ultra Apple48-Core M1 Ultra vs GPU Apple40-Core M5 Max Apple48-Core M1 Ultra vs GPU Apple40-Core M4 Max Show 12 more

NVIDIAGB10 vs GPU Apple60-Core M3 Ultra NVIDIAGB10 vs GPU Apple80-Core M3 Ultra NVIDIAGB10 vs GPU Apple40-Core M4 Max Show 3 more