AI Chip Startup MatX Raises $500M to Challenge Nvidia's GPU Dominance in LLM Training
By admin | Feb 25, 2026 | 1 min read
MatX, a semiconductor startup established by two former Google hardware engineers, has secured $500 million in a Series B funding round. The investment was spearheaded by Jane Street and Situational Awareness, an investment fund created by former OpenAI researcher Leopold Aschenbrenner. The company aims to develop processors that are ten times more effective for training large language models and delivering results compared to Nvidia’s GPUs.
Additional participants in this funding round include Marvell Technology, NFDG, Spark Capital, and Stripe co-founders Patrick Collison and John Collison. MatX’s founder and CEO, Reiner Pope, shared this announcement in a LinkedIn post on Tuesday.
While the startup has not disclosed its current valuation, its closest competitor, Etched, recently raised $500 million at a $5 billion valuation, as reported last month. Etched has not yet provided a comment on this development.
This latest funding follows MatX’s Series A round of approximately $100 million, which was led by Spark Capital over a year ago. Before co-founding MatX in 2023, Reiner Pope was responsible for AI software development for Google’s proprietary AI chips, known as TPUs. His co-founder, Mike Gunter, previously served as a lead designer for TPU hardware before departing to launch the startup.
The newly acquired capital will support MatX in manufacturing its chips through TSMC, with plans to commence shipments in 2027.
Comments
Please log in to leave a comment.
No comments yet. Be the first to comment!