{"city":null,"name":"MatX","slug":"matx","facts":[{"date":"2026-09-14","type":"revenue_band","value":"pre-revenue","source":"MatX"},{"date":"2026-09-14","type":"partnership","value":"Jane Street, Spark Capital, and other investors are among MatX's backers.","source":"MatX"},{"date":"2026-06-15","type":"total_funding","value":"USD 500000000","source":"Innatera"},{"date":"2026-02-24","type":"product_launch","value":"Ship 2027.","source":"Bloomberg, TechCrunch, DCD"},{"date":"2026-02-24","type":"partnership","value":"Jane Street and Situational Awareness led the Series B; Marvell is a strategic investor.","source":"Bloomberg, TechCrunch, DCD"},{"date":"2026-02-24","type":"funding_round","value":"Series B led by Jane Street and Situational Awareness; Marvell strategic.","source":"Bloomberg, TechCrunch, DCD"}],"peers":[],"stage":null,"state":null,"aliases":["MatX One"],"country":"United States","domains":[{"why":"MatX is developing MatX One, an AI accelerator that keeps model weights in SRAM for high-throughput, low-latency inference on large models in very large clusters.","list":null,"rank":null,"tier":"watchlist","layer":null,"total":54,"domain":"AI Core","scores":{"leverage":8,"position":4,"progress":8,"firepower":8,"commercial":2,"deployment":2,"production":4,"technology":6},"edition":null,"segment":null}],"founded":null,"signals":[{"date":"2026-09-14","header":"MatX One supports scale-out clusters with hundreds of thousands of chips.","outlet":"MatX"},{"date":"2026-09-14","header":"MatX provides a programming model with direct hardware control.","outlet":"MatX"},{"date":"2026-09-14","header":"MatX One claims leading throughput and latency for large-model workloads.","outlet":"MatX"},{"date":"2026-09-14","header":"MatX One uses SRAM-resident weights to support high-throughput LLM inference.","outlet":"MatX"},{"date":"2026-09-14","header":"MatX lists Jane Street, Spark Capital, and other investors among its backers.","outlet":"MatX"},{"date":"2026-06-15","header":"MatX raised $500 million to develop AI semiconductors.","outlet":"Innatera"}],"website":"matx.com","category":"AI Infra · Chips & accelerators","categories":[{"name":"Inference-specialist chips","domain":"AI Core","parent":"AI Infra · Chips & accelerators"}],"last_round":null,"updated_at":"2026-09-22T22:24:32.973+00:00","facts_total":10,"positioning":"Ex-Google TPU founders building an LLM-specific chip (SRAM-first with HBM) at TSMC for 2027 shipment; $500M Series B from Jane Street and Situational Awareness with Marvell as strategic investor.","sub_category":"Inference-specialist chips","signals_total":6,"url":"https://www.frontiertechintelligence.com/companies/matx","title":"MatX · ai core, United States · scores, facts and signals · Frontier Tech Intelligence","description":"MatX is developing MatX One, an AI accelerator that keeps model weights in SRAM for high-throughput, low-latency inference on large models in very large clusters. AI Core watchlist (score 54) 6 signals and 10 facts with sources.","publisher":"Frontier Tech Intelligence (Future Frontiers, a trade name of Essential Cognition Inc.)","note":"Assessment by Frontier Tech Intelligence; facts and signals carry their sources."}