★
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 › AMD Instinct MI400 / MI450

AMD Instinct MI400 / MI450

Chip GPU Ramping

AMD's 2026 rack-scale answer — and the chip behind the OpenAI 6-gigawatt deal.

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.

The MI400 series, announced for 2026, targets 432 GB of HBM4 and roughly 40 PFLOPS of FP4 per GPU, shipping in the 72-GPU 'Helios' rack platform. In October 2025 OpenAI and AMD announced a multi-year agreement to deploy up to 6 gigawatts of Instinct GPUs beginning with MI450 in late 2026 — with an equity warrant structure — the strongest customer endorsement AMD's AI line has received. All figures are announced targets.

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 AMD
Status Announced for 2026
Flagship commitment OpenAI: up to 6 GW of Instinct deployment starting with MI450 in 2H 2026Reported

Memory

Memory (announced) 432 GB HBM4, ~19.6 TB/sVendor claim

Compute

FP4 (announced) ~40 PFLOPSVendor claim

Physical

Platform Helios rack — 72 GPUs, doubling as AMD's NVL72 answerVendor claim

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

AMD

Manufactured by

Memory technology

Interconnect & networking

Found inside

Successor to

Competes with

Sources

AMD–OpenAI announcement (Oct 2025) ↗

Record reviewed as of 2026-08-31 — see Methodology.