HyperAIHyperAI

Command Palette

Search for a command to run...

3 months ago
LLM
GPU

AI chip startup MatX raises $500M to challenge Nvidia, aims for 10x faster LLM training with TSMC-built chips launching in 2027

MatX, a startup founded by two former Google hardware engineers, has raised $500 million in a Series B funding round led by Jane Street and Situational Awareness, an investment fund established by Leopold Aschenbrenner, a former OpenAI researcher. The company aims to develop AI processors that are 10 times more efficient than Nvidia’s GPUs in training large language models and delivering results. Other investors in the round include Marvell Technology, NFDG, Spark Capital, and Stripe co-founders Patrick Collison and John Collison. CEO and founder Reiner Pope announced the news on LinkedIn on Tuesday. While MatX did not disclose its current valuation, its closest competitor, Etched, recently raised $500 million at a $5 billion valuation, according to Bloomberg. Etched did not respond to a request for comment. This latest round follows a $100 million Series A in 2023, also led by Spark Capital. TechCrunch previously reported that the 2024 funding round valued MatX at more than $300 million. Before founding MatX in 2023, Pope led AI software development for Google’s Tensor Processing Units (TPUs), the company’s custom AI chips. His co-founder, Mike Gunter, served as a lead hardware designer for the TPU program before leaving Google to launch the startup. The new capital will support MatX’s chip production through a partnership with TSMC, with plans to begin shipping its first processors in 2027. The company is positioning itself as a serious challenger to Nvidia’s dominance in the AI chip market, focusing on performance, efficiency, and scalability for next-generation AI workloads.

Related Links

AI chip startup MatX raises $500M to challenge Nvidia, aims for 10x faster LLM training with TSMC-built chips launching in 2027 | Trending Stories | HyperAI