Our Gaudi2 accelerator
is driving improved deep learning price-performance

and operational efficiency for training and running state-of-the-art models, from the largest language and multi-modal models to more basic computer vision and NLP models. Designed for efficient scalability—whether in the cloud or in your data center, Gaudi2 brings the AI industry the choice it needs—now more than ever.

Gaudi2 architectural features:
built on the proven Gaudi design foundation

  • 7nm process technology
  • Heterogeneous compute
  • 24 Tensor Processor Cores
  • Dual matrix multiplication engines
  • 24 100 Gigabit Ethernet integrated on chip
  • 96 GB HBM2E memory on board
  • 48 MB SRAM
  • Integrated Media Control
Gaudi2 board

Gaudi2® in the Cloud

Discover the performance and ease of use Gaudi2 provides on the Intel Developer Cloud.

And coming soon: Gaudi2 on the Genesis Cloud.

Learn more

Gaudi2® in the Data Center

Bring the price-performance advantage into your infrastructure with solutions from Supermicro and IEI.

Learn more

Gaudi2 Training and Inference Performance

Gaudi2 delivers choice.

Based on MLPerf Training 3.0 Results published June 2023, Gaudi2 is the ONLY viable alternative to H100 for training
large language models like GPT-3. Read the details >

In addition to the MLPerf industry benchmark, Gaudi2 scores on other third-party evaluations.

For a topline on Gaudi2 Please Watch>

Gaudi2 supports massive, flexible scale out.

With 24x 100 Gigabit Ethernet (RoCEv2) ports integrated onto every Gaudi2, customers benefit from flexible and cost-efficient scalability that extends Gaudi2 performance from one to thousands of Gaudi2.

Figure1: Gaudi 8 accelerator reference design

Gaudi2 Scale out

For more information on building out system scale with Gaudi2, see our Networking with Gaudi page >

Easily build new or migrate
existing models on Gaudi2

Synapseai grey logo

SynapseAI Software Stack, optimized for Gaudi platform performance and ease, gives developers the documents, tools, how-to content and reference models to help developers get started on Gaudi quickly and
with ease.

Access and easily implement over 50,000 models with Habana Optimum Library on the Hugging Face hub.
For more information, see our developer site >

Synapse ecosystem

How2 with Gaudi2

Buy icon

Access / Buy

Learn More
develop icon


Learn More


Learn More
partner icon


Learn More