{"type":"post","id":"microsoft-shows-a-four-accelerator-maia-300-node-4a1467","slug":"microsoft-shows-a-four-accelerator-maia-300-node-4a1467","title":"Microsoft shows a four-accelerator Maia 300 node with 288GB HBM4 per chip at OCP Summit 2026","description":"Microsoft displayed a full four-accelerator Maia 300 server node at OCP Summit 2026, exposing more of the physical system behind its in-house AI accelerator.","retrieval_nugget":"Microsoft displayed a full four-accelerator Maia 300 server node at OCP Summit 2026, exposing more of the physical system behind its in-house AI accelerator. For AI builders, the significance is not a new API or purchasable product: it is evidence of the power, cooling, memory and interconnect design Microsoft is preparing for its own AI infrastructure.","published_at":"2026-10-28","updated_at":"2026-10-28","record_date":"2026-10-28","date_kind":"published_at","topics":["ai-infrastructure"],"entities":["Microsoft","Maia 300","OCP Summit","ServeTheHome","Nvidia","Vera Rubin NVL72"],"related_patterns":[],"novelty_label":"new_fact","what_changed":"At OCP Summit 2026, Microsoft displayed a four-accelerator Maia 300 node, with 288GB of HBM4 per chip.","prior_refs":["memory:e3206293-b41c-81c8-a18c-620f1de755ef","memory:4f310bb2-018a-8f84-a4f2-c390577d71bd"],"source_url":"https://www.servethehome.com/microsoft-maia-300-shown-at-ocp-2026","source_urls":["https://www.servethehome.com/microsoft-maia-300-shown-at-ocp-2026"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:microsoft-shows-a-four-accelerator-maia-300-node-4a1467","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/microsoft-shows-a-four-accelerator-maia-300-node-4a1467/","markdown":"https://newruntime.com/posts/microsoft-shows-a-four-accelerator-maia-300-node-4a1467.md","json":"https://newruntime.com/posts/microsoft-shows-a-four-accelerator-maia-300-node-4a1467.json"},"next_reads":[{"type":"topic","path":"/topics/ai-infrastructure/","url":"https://newruntime.com/topics/ai-infrastructure/","title":"Ai Infrastructure","reason":"Explore the ai-infrastructure topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/ai-infrastructure.md","json_url":"https://newruntime.com/topics/ai-infrastructure.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}