AI companies are racing to build bigger models, but those models need massive processing power. On the other end of the spectrum, some researchers and startups are building smaller models that run on edge devices like phones and computers. One such startup, Underdog, released a game built with its new voice model called Woof, which is only 32MB large.

The game features a room with a retro tech theme, a typewriter, and a CRT monitor. A desk lamp makes a sound when you click its switch, and the intro warns users about “intrusive” cloud providers in the town — ostensibly a jab at cloud-based models. You can interact with the typewriter and a music tuner. Typing on the typewriter causes the game to speak the text back, and rotating the tuner generates different kinds of music. All of this works within the browser through Underdog’s speech generation model, which the company says can run on most devices without any internet connection. The model has 31 million parameters and is open for everyone to download.

The demo comes weeks after Underdog launched Bark, a 167MB speech-to-text model also designed to run on edge devices for transcription and dictation. Founder Sigil Wen told TechCrunch that he started building the app because, instead of using notetakers like Granola, he wanted to build his own system with AI models that can run on users’ devices and let them own their data. “I think we will be able to run most capable models of today on the devices you already own within months. We just want to train the best open models that are American-made, that are open, that are capable and allow people to have private AI,” he said, referring to his manifesto.

Underdog has also released a 27-billion-parameter model that can run on laptops, along with a waitlisted app that the company is positioning as a locally-hosted alternative to Muse and Instinct. While such a small model likely won’t replace bigger models, it may still be enough to drive local assistant experiences or create personalized podcasts.