Hugging Face

Build Small Winners Reveal

Published 2026-07-10 · Duration 53:45

Summary

The Build Small Hackathon winners reveal celebrated projects that emphasize building highly functional applications using small, efficient models and local/on-device processing. The community demonstrated a strong focus on 'local first' AI solutions, achieving impressive metrics like 64% of apps running fully offline. Winning projects showcased practical utility—such as scam defense (Jawbreaker) or specialized coaching (Posify)—proving that powerful, real-world impact can be achieved with tiny model footprints.

Download summary

Key takeaways

  1. Focus on Local and Small Models 18:05

    The hackathon emphasized building small apps using sub-32 billion parameter models. Key metrics showed that 64% of submissions ran fully offline, highlighting the viability of 'local first' AI architectures.

  2. High Utility in Niche Applications 27:20

    Winning projects demonstrated significant real-world utility. Examples include Jawbreaker (a private scam defense tool for suspicious text/emails) and Agenda Parser (breaking down dense local government agendas), proving the value of small, focused solutions.

  3. Advanced Technical Implementation 30:30

    Winners utilized advanced techniques like WebGPU for browser-based real-time games (Parry) and quantization methods (GGUF) to drastically reduce cold boot times, demonstrating high technical polish.

  4. Open Source Model Ecosystem 22:20

    The most popular model family used was Qwen (288 spaces), followed by MiniCPM OpenBMB and Nematron, confirming the community's reliance on diverse open-source models.

Technical details

  • Submission Metrics 1230s

    Out of 946 total spaces, 850 were Gradio Spaces. The deadline rush was notable, with 40% of all submissions arriving in the final 48 hours.

  • Model Usage and Efficiency 1340s

    While the premise required sub-32B parameter models, only 19% actually did so. However, 367 apps used models below 4 billion parameters, and 64% ran fully offline.

  • Model Orchestration 1500s

    One winning app (Viva Mice) was notable for using 21 distinct models in a single application, demonstrating intelligent model selection and orchestration rather than just thin wrappers.

  • Frameworks and Tools 1580s

    Specific tools used included Modal (336 spaces), OpenBMB models (309 spaces), Nvidia models (199 spaces), and OpenAI's Codex (137 spaces) for development assistance.

Mentioned resources

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.