NVIDIA H200 SXM vs NVIDIA GB200 Full Specs

Summary

16,896 Shaders 1.98GHz	37,888 Shaders 2.11GHz
141GB HBM3e4.81TB/s	384GB HBM3e16TB/s
Peak·FP32·FP16 66.91 TFLOPS	Peak·FP32·FP16 160 TFLOPS
Form Factor SXM5	Form Factor Superchip
TDP 700W	TDP 2700W

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 Tensor FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Memory Bandwidth TDP

H200 SXM3.96 POPSINT8 Tensor Sparse

x1

GB20040 PFLOPSFP4 Tensor Sparse (2x 20 PFLOPS)

x10.11

Show Top Score

Theoretical Performance

Clock Speed1980MHz UC·Base·Boost·OC	Clock Speed2112MHz UC·Boost·OC
Peak OPS 3.96 POPSINT8 Tensor Sparse	Peak OPS 40 PFLOPSFP4 Tensor Sparse
-	Tensor FP4 20 PFLOPS FP4 Tensor Sparse 40 PFLOPS
Tensor FP8-16 1.98 PFLOPS FP8-16 Tensor Sparse 3.96 PFLOPS Tensor FP8-32 1.98 PFLOPS FP8-32 Tensor Sparse 3.96 PFLOPS	Tensor FP8-16 10 PFLOPS FP8-16 Tensor Sparse 20 PFLOPS Tensor FP8-32 10 PFLOPS FP8-32 Tensor Sparse 20 PFLOPS
Tensor FP16-16 989.4 TFLOPS FP16-16 Tensor Sparse 1.98 PFLOPS Tensor FP16-32 989.4 TFLOPS FP16-32 Tensor Sparse 1.98 PFLOPS	Tensor FP16-16 5 PFLOPS FP16-16 Tensor Sparse 10 PFLOPS Tensor FP16-32 5 PFLOPS FP16-32 Tensor Sparse 10 PFLOPS
BF16 133.8 TFLOPS Tensor BF16 989.4 TFLOPS BF16 Tensor Sparse 1.98 PFLOPS	BF16 320.1 TFLOPS Tensor BF16 5 PFLOPS BF16 Tensor Sparse 10 PFLOPS
Tensor TF32 494.7 TFLOPS	Tensor TF32 2.5 PFLOPS
FP32 66.91 TFLOPS	FP32 160 TFLOPS
FP64 33.45 TFLOPS Tensor FP64 61.84 TFLOPS	FP64 80.02 TFLOPS Tensor FP64 78.13 TFLOPS
Tensor INT8 1.98 POPS	Tensor INT8 10 POPS
Pixel Rate 47.5 GPixel/s	Pixel Rate 67.6 GPixel/s
Texture Rate 1.04 TTexel/s	Texture Rate 1.25 TTexel/s

Core Config

Shaders 16,896 Shaders	Shaders 37,888 Shaders
TMUs 528 TMUs	TMUs 1,184 TMUs
ROPs 24 ROPs	ROPs 64 ROPs
Tensor Cores 528 T-Cores	Tensor Cores 1,184 T-Cores
SMs 132 SMs	SMs 296 SMs

Clocks

Base Clock 1.06GHz	Base Clock -
Boost Clock 1.98GHz	Boost Clock 2.11GHz
Tensor Clock 1.83GHz	Tensor Clock 2.06GHz

Cache

L2 Cache 51.2MB shared

L2 Cache 65.5MB shared

Memory

141GB HBM3e	384GB HBM3e
Memory Bus 6144-bit	Memory Bus 8192-bit
Memory Speed 6.3GT/s	Memory Speed 7.8GT/s
Memory Bandwidth 4.81TB/s	Memory Bandwidth 16TB/s

Power & Thermals

TDP 700W

TDP 2700W

Decoder

Decoder Model 7x NVDEC 5

Decoder Model 7x NVDEC 6

Card

Form Factor SXM5	Form Factor Superchip
Cooling Passive	Cooling Passive

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Hopper	Architecture Blackwell
Family Server	Family Server
Branding	Branding
Codename NV180	Codename NV190
Chip Variant -	Chip Variant Umbriel
Market Segment Server	Market Segment Server
Release Date Nov 13, 2023	Release Date Mar 18, 2024

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4N	Fabrication Node 4NP
Die Size 814mm²	Die Size 1620mm²
Transistor Count 80 Billion	Transistor Count 208 Billion
Transistor Density 98.28 MTr/mm²	Transistor Density 128.4 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAH200 SXM vs GPU NVIDIAB100 NVIDIAH200 SXM vs GPU NVIDIAB200 NVIDIAH200 SXM vs GPU IntelGaudi 3 Show 12 more

NVIDIAGB200 vs GPU NVIDIAB200 NVIDIAGB200 vs GPU NVIDIAB100 NVIDIAGB200 vs GPU NVIDIAL40 Show 12 more