Trending Repos

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM, and VRAM into a single intelligent memory hierarchy, enabling inference of models like GPT-OSS 120B, GLM, DeepSeek, Qwen, and more on consumer hardware