★
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 › Servers & Systems › AWS Trn2 UltraServer

AWS Trn2 UltraServer

System AI Server Shipping

64 Trainium2 chips fused by NeuronLink — the block Rainier is built from.

You're looking at a system record: an assembled machine — a server or a whole rack — with what's inside it and where it's deployed.

AWS's UltraServer joins four Trn2 instances (64 chips) into one NeuronLink domain: 6 TB of HBM and 83 PFLOPS of dense FP8 per unit. Project Rainier stacks thousands of them with EFA networking — Amazon's rack-scale answer assembled from cloud primitives rather than a monolithic rack product.

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

Configuration 64 × Trainium2 across 4 nodes, NeuronLinkVendor spec

Memory

HBM 6 TB per UltraServerVendor spec

Compute

FP8 dense 83.2 PFLOPSVendor 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

Contains

Sources

AWS Trn2 ↗

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