Chip startup FuriosaAI is reportedly seeking to raise between $300 and $500 million in a funding round ahead of its anticipated IPO.

According to a report from Bloomberg, Furiosa has appointed Morgan Stanley and Mirae Asset Securities as co-advisors for the Series D round. The funding will be used to support the mass production of the company’s second-generation RNGD chip.

Founded in 2017 and headquartered in South Korea's capital, Seoul, to date, FuriosaAI has raised approximately $115 million across four funding rounds. In March 2024, the startup turned down an $800m acquisition offer from Meta, with the startup reportedly wanting to grow its business as an independent company instead.

Furiosa’s RNGD chip is built using the company’s Tensor Contraction Processor chip architecture, with the AI inference chip delivering 512 teraflops of FP8 performance with a thermal design power (TDP) of 150W. When compared to Nvidia’s H100 GPUs – which have a TDP of 350W – RNGD offers 3x better performance per watt, the company claims.

In September 2025, Furiosa launched its NXT RNGD server. Designed for on-premise and private cloud AI workloads, the sever is powered by eight RNGD cards and uses 3kW of power to deliver four petaflops of FP8 compute in a single standard 4U unit.

Per the Bloomberg report, FuriosaAI is set to receive its first mass-produced shipment of RNGD AI chips from TSMC later this month.