London startup Fractile raised a $220 million Series B led by Accel, Factorial Funds and Founders Fund to attack the inference bottleneck with a memory-centric chip design.
What changed
Fractile says current inference hardware leaves frontier models stuck around tens of tokens per second for difficult reasoning workloads.
CEO Walter Goodwin is pitching a design that avoids both HBM and conventional on-chip SRAM, moving toward in-memory compute rather than a better GPU clone.
Why it matters
The company has not yet disclosed customers, production timing, benchmark numbers or quantified power savings, so the round is still a bet on architecture.
What to watch
The useful signal is not the headline number alone, but whether the product, contract or platform shift becomes repeatable over the next two quarters.
Sources: CocoLoop