- Fractile has raised $220 million in a funding round led by Accel, Factorial Funds, and Founders Fund.
- Founded in 2022 by Oxford researcher Walter Goodwin, the startup is building specialised chips to dramatically speed up AI inference.
- Fractile aims to bring its first systems to customers while expanding operations across the UK, US, and Taiwan.
London-based startup Fractile has secured $220 million in fresh funding to push that vision forward. The round was led by Accel, Factorial Funds, and Founders Fund, with participation from Conviction, Gigascale, O1A, Felicis, Buckley Ventures, and 8VC.
Founded in 2022 by Oxford-trained engineer Walter Goodwin, alongside co-founder Yuhang Song, Fractile was built around a bold assumption that future AI progress would eventually be constrained not by model capability, but by how long systems take to generate useful outputs. Goodwin previously researched robotics and computing systems at the University of Oxford before launching the company to rethink AI hardware from scratch.
The startup is focused on inference, the stage where trained models generate answers and perform reasoning tasks. Fractile claims that today’s hardware struggles with increasingly long-context workloads because memory bandwidth has failed to scale efficiently. Some advanced models already produce outputs involving tens of millions of tokens, with certain workloads taking weeks to complete on conventional chips.
To tackle this, Fractile is developing specialised hardware architectures aimed at dramatically improving inference speed and reducing costs. The company claims its systems could eventually increase performance from roughly 40 tokens per second on existing hardware to around 1,200 tokens per second. Its broader goal is to compress workloads that currently take a month into a single day.
The company enters a fiercely competitive market dominated by NVIDIA and challenged by rivals such as AMD, Cerebras, and Groq. Fractile is positioning itself differently by focusing around ultra-fast inference for large-scale reasoning and long-context computing.
Looking ahead, the company sees opportunities extending beyond coding assistants into drug discovery, software engineering, and materials science. Fractile is now hiring across London, Bristol, San Francisco, and Taipei as it prepares for global expansion and commercial deployment in the coming years. The capital will also support the launch of Fractile’s first chips and systems for customers.
