Vibeleaderboard
Index / tool
Visit github.com
Category
Developer Tools
Pricing
Open Source
Type
TOOL
Latest release
v1.10.2
Date

About

Colibri is a pure-C inference engine that runs large mixture-of-experts language models, from 744B up to 2.8T parameters, on consumer hardware by treating disk, RAM, and VRAM as a single memory hierarchy and streaming experts from storage. It supports eight model families, including GLM-5.2/5.3, Kimi K3, and DeepSeek V4 Flash, with zero external engine dependencies.

Why it made the leaderboard

It lets developers run enormous MoE models locally by treating disk, RAM, and VRAM as one inference hierarchy, opening frontier-scale model experimentation to people without datacenter GPUs.

Tags

llminferencemoeclocal-aiopen-source

Tech Stack

Python

Comments (0)

No comments yet

Editorially curated, with community endorsements as a secondary signal. Corrections welcome.