★
Menu
Home How It's Built Watchlist The Stack
Hardware ChipsCompare Chips Servers & SystemsNetworking MemoryFoundries & Packaging Cooling
Facilities Data CentersPower ProjectsCloud & GPU Compute
Intelligence AI ModelsSoftware AI ProductsBenchmarks Research PapersDatasets Concepts
Ecosystem CompaniesStocks PeopleTimeline TrendsFuture of AI
Learn News Ask the Data AI Agents
About About us Methodology Data & API Disclaimer
Options
DATA & API

Free read-only JSON access to the site's cached data.

Dark mode

Guided View
New to chips, data centers and model jargon? We explain key terms as you browse, in plain English. Same data, with the help built in.

Expert View
You already know the stack. Just the data: clean, fast and compact, with no extra explanations. This is the default view.

Interface language
‹ Back
Home › Chips › NVIDIA GH200 Grace Hopper

NVIDIA GH200 Grace Hopper

Chip Superchip Shipping

A Grace CPU and Hopper GPU fused over NVLink-C2C into one coherent superchip.

You're looking at a chip record: what this processor is, its key specs, who designs, manufactures and supplies its parts, and where it gets used.

GH200 bonds a 72-core Grace CPU to an H100-class GPU with a 900 GB/s coherent link, giving the GPU direct access to up to 480 GB of LPDDR5X alongside its own HBM. It pioneered the CPU+GPU superchip pattern that GB200 scaled up, and powers systems like the Alps and Isambard-AI supercomputers.

Specifications & key facts

Each figure is labeled by basis: vendor spec, vendor claim, reported, estimate, or official. "Not publicly disclosed" means exactly that — we never invent values.

Overview

Designer NVIDIA
Architecture Grace CPU + Hopper GPU
Announced Full production May 2023

Memory

GPU memory 96 GB HBM3 (4 TB/s) or 144 GB HBM3E (4.9 TB/s)Vendor spec
CPU memory up to 480 GB LPDDR5XVendor spec

Physical

CPU 72 Arm Neoverse V2 cores (Grace)Vendor spec
Interconnect NVLink-C2C — 900 GB/s coherent CPU–GPU linkVendor spec

Power

Module power 450–1,000 W depending on configurationVendor spec

How this connects to the rest of the stack

This record's links at a glance — click a group to jump to it.

Designed by

Manufactured by

Memory technology

Interconnect & networking

Contains

Sources

NVIDIA GH200 page ↗

Record reviewed as of 2026-01-15 — see Methodology.