[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-microsoft-unveils-maia-300-inference-chip-for-2027":10,"sections":41},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":30,"tags":31,"sources":36,"feedback":40,"feedback_at":22,"cost_usd":40,"total_tokens":40},11384,"microsoft-unveils-maia-300-inference-chip-for-2027","Microsoft unveils Maia 300 inference chip for 2027","Microsoft's latest custom AI chip promises big efficiency gains for Copilot and Teams, but the improvements won't land until 2027.","Microsoft has unveiled Maia 300, a new AI chip designed to make its own AI products faster and cheaper to run - though it won't ship until 2027.\n\nThe chip is built specifically for inference rather than training, and Microsoft says a rack of 96 Maia 300 accelerators will deliver up to seven times the token throughput of an equivalent Maia 200 rack, alongside a claimed 40% more tokens per megawatt than competing GPU-based systems. It uses eight stacks of HBM4 memory with 18TB\u002Fs of peak bandwidth, draws up to 950W, and splits compute, memory-control and input\u002Foutput functions across separate chiplets built on TSMC's N2P process. Microsoft says the design leans on software-defined dataflow and AI-assisted kernel tuning to cut data movement, rather than simply adding more raw silicon.\n\nThe real audience here isn't outside hardware buyers - it's Microsoft's own product teams. Maia 300 is meant to underwrite everything from GitHub Copilot's agentic coding features to Microsoft Teams and Cowork, areas where slow AI responses are a visible daily annoyance rather than an abstract benchmark number. That continues the pattern set by Maia 200, which Microsoft says already runs Microsoft 365 Copilot and claims a 1.7x tokens-per-watt edge over GPU infrastructure for those same products.\n\nEvery efficiency figure here is Microsoft's own, measured against unnamed leading GPU-based systems, and the chip is still roughly a year from shipping - so the real test is how Copilot and Teams actually feel once it arrives. Still, Maia 300 continues Microsoft's push to treat in-house AI silicon as core infrastructure, the same bet Google and Amazon have made with their own custom chips.","[\"microsoft\",\"ai-chips\",\"azure\",\"copilot\"]","2026-10-12T13:00:00.000Z","2026-10-12T13:35:37.469Z","2026-10-12T13:35:41.015Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Remove or attribute the unsupported 'hundreds of millions of users' figure and the specific 'rented Nvidia GPUs' claim in the third paragraph — neither appears in the source material and both read as invented statistics\u002Fclaims.","resolved","hardware",[32,33,34,35],"microsoft","ai-chips","azure","copilot",[37],{"name":38,"url":39},"TechRadar","https:\u002F\u002Fwww.techradar.com\u002Fpro\u002Fmicrosoft-unveils-maia-300-its-most-powerful-ai-chip-yet-and-it-might-make-using-teams-copilot-and-cowork-much-better-at-last",0,{"sections":42},[43,48,53,58,63,67,72,77,82,87,92,97,102,107],{"name":44,"slug":45,"count":46,"latest_published_at":47},"AI","ai",6967,"2026-10-12T15:20:00.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Security","security",954,"2026-10-12T14:20:37.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Policy","policy",496,"2026-10-11T20:06:43.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Deals","deals",492,"2026-10-12T14:55:53.000Z",{"name":64,"slug":30,"count":65,"latest_published_at":66},"Hardware",237,"2026-10-12T13:24:45.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Science","science",196,"2026-10-11T15:34:40.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":76},"Consumer Tech","consumer-tech",192,"2026-10-12T14:07:13.000Z",{"name":78,"slug":79,"count":80,"latest_published_at":81},"Startups","startups",121,"2026-10-12T13:22:34.000Z",{"name":83,"slug":84,"count":85,"latest_published_at":86},"Software","software",115,"2026-10-11T07:34:45.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"Dev Tools","dev-tools",111,"2026-10-12T11:22:24.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"General","general",71,"2026-10-12T16:10:40.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"Gaming","gaming",59,"2026-10-09T11:43:43.000Z",{"name":103,"slug":104,"count":105,"latest_published_at":106},"Reviews","reviews",35,"2026-10-12T14:00:00.000Z",{"name":108,"slug":109,"count":110,"latest_published_at":111},"How-To","how-to",8,"2026-10-05T09:00:00.000Z"]