FuriosaAI has signed an agreement with LG AI Research that will see the South Korean chip startup’s RNGD (Renegade) chips supplied to enterprises via LG’s EXAONE platform.

First unveiled in 2021, EXAONE – or EXpert AI for EveryONE – is an LLM (large language model) developed by LG AI Research. This week, the company launched EXAONE AI, a family of LLMs (large language models) that includes both the foundational model and a number of variants developed to perform agentic roles across industries, including electronics, finance, telecommunications, and biotechnology.

According to LG AI Research, the company was able to achieve 2.25x better LLM inference performance per watt compared to an unnamed “GPU-based solution,” with an RNGD-powered rack able to generate 3.75x more tokens compared to a GPU rack operating with the same power constraints.

“After extensively testing a wide range of options, we found RNGD to be a highly effective solution for deploying EXAONE models. RNGD provides a compelling combination of benefits: excellent real-world performance, a dramatic reduction in our total cost of ownership, and a surprisingly straightforward integration," said Kijeong Jeon, product unit leader at LG AI Research. "For a project of this scale and ambition, the entire process was quite impressive.”

Founded in 2017 and headquartered in South Korea's capital Seoul, FuriosaAI has raised approximately $115 million across four funding rounds to support the development of its RNGD chip.

Built using the company’s Tensor Contraction Processor chip architecture, its AI inference chip delivers 512 terraflops of FP8 performance with a thermal design power (TDP) of 150W. RNGD servers comprise eight RNGD accelerators in a single, air-cooled 4U chassis, with a standard 15kW air-cooled rack able to host up to five servers.

FuriosaAI claims that when compared to Nvidia’s H100 GPUs – which have a TDP of 350W – RNGD offers 3x better performance per watt.

Earlier this year, the startup turned down an $800m acquisition offer from Meta, with the startup reportedly wanting to grow its business as an independent company instead.