Partnership To Boost Industry AI With Gaudi 3

Intel Gaudi 3 AI accelerators make IBM Cloud hybrid cloud solutions affordable, scalable, and easy to implement

This service helps organizations expand AI and innovate cost-effectively while prioritizing openness, security, and resiliency

IBM and Intel have a longstanding partnership to create AI systems with low total cost of ownership (TCO) and enable an open ecosystem to grow enterprise AI

IBM Watsonx and data platform connection is simplified by intel Gaudi 3 accelerators' multi-model LLMs and RAG.

Intel Gaudi 3 accelerators have 4x the computation, 2x the networking bandwidth, and 1.5x the memory bandwidth of Intel Gaudi 2

One card of Intel Gaudi 3 AI accelerators on IBM Cloud can generate over 5,000 tokens per second for IBM's granite-8b model, allowing over 100 concurrent users with less than 20 milliseconds inter-token latency

Enterprises may scale from a single node (eight accelerators) with 9.6 TB/s throughput to a 1,024-node cluster (8,192 accelerators) with 9.830 PB/s

IBM Cloud Virtual Servers for Virtual Private Cloud (VPC) with Intel Gaudi 3 AI accelerators let x86-based organisations run apps fast and securely, increasing user experiences

Chatbots, virtual assistants, code creation, natural language translations, and text summarization and paraphrasing are enterprise GenAI applications

Data management and a strategic hybrid cloud architecture can help IT directors make informed decisions to make data and AI easier to access and implement

In Q2 2025, IBM Cloud VPC clients can deploy IBM watsonx.ai on their Intel Gaudi 3-based virtual server for AI stack control

IBM Cloud clients may connect Intel Gaudi 3 with watsonx, IBM Cloud Virtual Server for VPC, Red Hat OpenShift, and Kubernetes Service DAs instantly