Meet the New AMD Instinct™ MI350 Series GPUs

The AMD Instinct™ MI350 Series GPUs set a new standard for Generative AI and high performance computing (HPC) in data centers. Built on the new cutting-edge 4th Gen AMD CDNA™ architecture, these GPUs deliver exceptional efficiency and performance for training massive AI models, high-speed inference, and complex HPC workloads like scientific simulations, data processing, and computational modeling.

Meet the MI350 Series
AMD Instinct™ MI350X Accelerators

Leadership Performance at Any Scale

AMD Instinct™ accelerators enable leadership performance for the data center, at any scale—from single-server solutions up to the world’s largest, Exascale-class supercomputers.

They are uniquely well-suited to power even the most demanding AI and HPC workloads, offering exceptional compute performance, large memory density, high bandwidth memory, and support for specialized data formats.

AMD Instinct MI350 Series

Under the Hood

AMD Instinct GPUs are built on AMD CDNA™ architecture, which offers Matrix Core Technologies and support for a broad range of precision capabilities—from the highly efficient FP4, FP6 and FP8 (including sparsity support for AI), to the most demanding FP64 for HPC.

Learn More

Portfolio

AMD Instinct MI350 Series GPUs

View Instinct MI350 Series

AMD Instinct MI300 Series GPUs

AMD Instinct APU

Powering the world’s #1 supercomputer, the AMD Instinct MI300A APU combines AMD Instinct GPUs and AMD EPYC™ processors with shared memory for enhanced flexibility, efficiency, and programmability1

View Instinct MI300A Specs
View Instinct MI300 Series

AMD Instinct MI200 Series

AMD Instinct MI250 GPU

Delivers outstanding performance for enterprise, research, and academic HPC and AI workloads

View Instinct MI250 Specs

AMD Instinct MI210 GPU

Powers enterprise, research, and academic HPC and AI workloads for single-server solutions and more

View Instinct MI210 Specs
View Instinct MI200 Series

AMD ROCm™ Software

AMD ROCm™ software includes a broad set of programming models, tools, compilers, libraries, and runtimes for AI models and HPC workloads targeting AMD Instinct GPUs.

About ROCm
ROCm Developer Hub

Find Solutions

Experience AMD Instinct GPUs in the Cloud

Support your AI, HPC, and software development needs with programs supported by leading cloud service providers.

Learn about Instinct Cloud Options
Abstract data center interior with glowing lights
AMD Instinct MI350 Series

AMD Instinct GPU Partners and Server Solutions

AMD collaborates with leading Original Equipment Manufacturers (OEMs), and platform designers to offer a robust ecosystem of AMD Instinct GPU-powered solutions.

Find Instinct Solutions

Case Studies

View All
Ultra Ethernet Consortium logo

Ultra Ethernet Consortium

AMD is a founding member of the Ultra Ethernet Consortium, which aims to deliver a complete architecture that optimizes Ethernet for AI and HPC networking.

More on UEC
OpenXLA logo

OpenXLA

AMD is a founding member of Google’s OpenXLA Project, which streamlines developers’ ability to optimize their models to target a wide variety of hardware, including AMD Instinct accelerators.

Read OpenXLA Blog
Mosaic ML logo

MosaicML

MosaicML, along with AMD Instinct accelerators, simplifies training and deploying LLMs and other generative AI models.

Read MosaicML Blog
LUMI case study

LUMI

EuroHPC’s LUMI supercomputer, powered by HPE solutions featuring AMD Instinct accelerators, is advancing groundbreaking scientific research to solve some of the world’s toughest challenges.

More on LUMI

Resources

Stay Informed

Sign up to receive the latest data center news and server content.

Sign Up
Footnotes
  1. Top 500 list, November 2024