@GPTWare: Uhhhh WTF is this???
Summary
Colibri runs the 744B parameter GLM-5.2 MoE model on a laptop with 25GB RAM by activating only ~40B parameters per token and streaming experts from disk, all in a single 2,400-line C file with no GPU required.
View Cached Full Text
Cached at: 07/11/26, 11:23 AM
Uhhhh WTF is this??? 👀👀👀
Zane Chen (@chenzeling4): 744B parameters. On a laptop. With 25GB RAM.
Colibri runs GLM-5.2 (744B MoE) in pure C with zero dependencies. The trick: only ~40B params activate per token, so it keeps the dense part resident and streams experts from disk on demand. A single 2,400-line C file. No GPU, no
Similar Articles
@ErickSky: Forget about vLLM, llama.cpp, and expensive GPUs. [colibri] This runs GLM-5.2 (744B MoE) on ~25 GB of RAM with pure C a…
colibri is a pure C inference tool that runs the GLM-5.2 744B MoE model on ~25 GB RAM by streaming experts from disk, eliminating the need for expensive GPUs.
Colibri Hands-on: Running GLM 5.2 (744B) Locally without GPU
Colibri enables running the 744B-parameter GLM 5.2 model locally on CPU, making large-scale AI accessible without GPU hardware.
Show HN: Getting GLM 5.2 running on my slow computer
Colibrì is a pure C inference engine that runs the 744B GLM-5.2 MoE model on consumer hardware with ~25GB RAM by streaming experts from disk, achieving ~2.2-2.8 tokens/second with speculative decoding.
@yibie: Recommend this project—a single person wrote an inference engine in pure C, making the 744-billion-parameter GLM-5.2 run on a consumer machine with 25GB RAM. No GPU, no BLAS, no Python runtime—about 1300 lines of C. The core insight is simple: MoE…
Colibri is an inference engine written in pure C, approximately 1300 lines of code, zero dependencies. It can run the 744-billion-parameter GLM-5.2 MoE model on a consumer machine with 25GB RAM, achieved by streaming loaded routing experts and efficient caching, no GPU or Python runtime needed.
@danveloper: Now everyone does it
Zane Chen demonstrates Colibri, which runs GLM-5.2 (744B MoE) on a laptop with 25GB RAM using pure C and CPU-only inference, by streaming experts from disk.