Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
- Recommended by
- 3
- GitHub stars
- 46k
- Licence
- Apache-2.0
- Language
- C
- Last commit
- 2 Nov 2026
What people said
“I'm really excited about what's been happening couple last weeks for local inference. I feel like it all started after colibri was released. Great work! Anyone got recommendation about what local model to use for what purpose? I feel like (as they were saying in moonshot bl…”
“The thing that blows me away is it does this at one quarter the total parameter count of K3 (and 40% active parameter count). There's plenty of room at the bottom. > How are you all toying with running this kind of thing in a mega quantized way locally? Sure, let me answer that i…”
“Show HN: Getting GLM 5.2 running on my slow computer (937 points)”
Not software, abandoned or listed by mistake? Report this listing