Port real models. Run them on real silicon. Share the results. โก
This is a community hackathon for people who want to make open AI workloads run closer to the edge: vision, speech, audio, local language models, robotics, drones, and weird benchmark ideas that deserve to touch hardware. ๐ค
First step: join the Hugging Face organization so you show up with the rest of the teams, follow shared resources, and get the latest hackathon updates.
Bring your teammates too. The org page is the public roster for people, teams, models, demos, and board results around the hackathon. ๐
| Quest | What you can build |
|---|---|
| ๐๏ธ Vision | Denoising, detection, camera-first edge workloads |
| ๐๏ธ Speech + audio | Whisper-style kernels and streaming-friendly pipelines |
| ๐ง Local LLMs | GGUF and llama.cpp flows on ET-backed runtimes |
| ๐ค Robotics + drones | Perception, control, and low-power deployment paths |
| โ๏ธ Systems | Faster kernels, better memory movement, cleaner board runners |
| ๐งช Wildcard | Bring your own open model and make the benchmark reproducible |
The model repo is the technical home for examples, docs, benchmark artifacts, and the submission path:
Start from an existing port, improve a kernel, add a new model, or package a small demo that shows why your port matters.
Join Discord and ask in #Lab:
Tell us what you want to port, what hardware access you need, and whether you are looking for teammates.