BIO

Kevin & Tianqi are veteran engineers from Microsoft Surface devices and Qualcomm’s efficient-AI—that is miniaturizing enterprise-grade inference into badge-sized hardware, they designed the hardware + software of distiller, and enclosure to squeeze 3-billion-parameter language models into a 10-Watt, pocket-safe form factor, giving clinicians instant, private access to AI reasoning right at the bedside.

ABSTRACT

The Bio / medical industry creates huge amounts of data—vital-sign streams, imaging, clinician notes— Knowledge base requirements are very heavy, so a little help from a specialized llm can boost the productivity alot. Our new layered technology, accomplishes just this

Hardware layer: A customized CM5 board, an RP2040 co-processor, and a sunlight-readable E-ink display strike the sweet spot LLM entirely on-device + many other transcription models + TTS models.

Software layer – Our “MCP Hub” turns plain-language requests like “track heart rate every five minutes” into a reliable data log, even when Wi-Fi is down. With the help of AI coding, any sensor can start to work within 5min.