With $720M round, Britain’s Fractile gets a leg up in the race for AI chips
Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.
Fractile raised $720 million and says it will ship its first AI chips and systems next year, using a stacked-DRAM design plus its own ML compiler to attack LLM inference speed and cost. For teams running agentic workloads, the relevant bet is higher memory bandwidth/capacity without the usual latency trade-off, but adoption will likely mean evaluating a new full-stack hardware/compiler target rather than treating it as a drop-in GPU alternative.
Fractile has raised $720 million to develop AI chips that stack DRAM on top of processing units, potentially bypassing the memory-capacity trade-off limiting current AI model execution. This enables shipping large language models and agentic AI with longer task chains without compromising speed, a critical constraint for production environments. It may significantly reduce inference costs for LLMs and agents.