★
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 MI355X

AMD Instinct MI355X

Chip GPU Shipping

CDNA4 on 3 nm: 288 GB HBM3E, FP4/FP6 support, and Blackwell-class ambitions.

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.

Launched June 2025, the MI355X moves AMD to TSMC N3P and 185 billion transistors, adds FP4 and FP6 datatypes, and carries 288 GB of HBM3E at 8 TB/s. AMD's published figures — 10.1 PFLOPS FP8, 20.1 PFLOPS FP4 — put it in direct contention with Blackwell, and OpenAI, Meta, Microsoft and Oracle all appeared as named customers or partners during 2025. The liquid-cooled MI355X runs to 1,400 W.

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
Architecture CDNA 4, chiplet
Announced Launched June 2025
Status Shipping

Manufacturing

Foundry / process TSMC N3P compute diesVendor spec
Transistors 185 billionVendor spec

Memory

Memory 288 GB HBM3EVendor spec
Memory bandwidth 8 TB/sVendor spec

Compute

FP8 (dense) 10.1 PFLOPSVendor spec
FP6/FP4 (dense) 20.1 PFLOPSVendor spec
BF16 (dense) 5.0 PFLOPSVendor spec

Power

TDP 1,400 (liquid) / MI350X 1,000 (air) WVendor spec

Physical

Form factor OAM; 8-GPU UBB platform

How this connects to the rest of the stack

This record's links at a glance — click a group to jump to it. +3 more groups below.

Designed by

AMD

Manufactured by

Process node

Packaging

Memory technology

Supported by

Available from

Successor to

Sources

AMD Advancing AI 2025 announcement ↗

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