JustVugg/colibri
Run frontier MoE models on hardware you already own
JustVugg/colibri is a pure C inference engine for running frontier MoE models locally on hardware users already own. Recent GitHub Trending listings describe it as a tiny engine that streams expert weights from disk, aiming to lower memory and hardware requirements for local MoE inference.
Run frontier MoE models on hardware you already own
Pure C engine to run frontier MoE models locally
Run frontier MoE models on existing hardware, pure C
Run frontier MoE models on your existing hardware.
Run frontier MoE models on commodity hardware with pure C.
Tiny C engine to run frontier MoE models, experts streamed from disk