Running GLM-5.2 on a 25GB Machine
paulabartabajo_ · x · 2026-07-13
The author claims it is possible to run the near-frontier GLM-5.2 on a 25GB RAM machine, albeit "very slowly."
The focus here isn't the model's parameters, but rather a somewhat hacky yet elegant open-source contribution: it demonstrates that the "memory wall" isn't absolute, and large models can indeed be squeezed onto smaller machines. The author also encourages dropping a star on the GitHub project.
Related event: COLIBRI Runs 744B GLM-5.2 Model on 25GB RAM Without GPU(3 posts)→
More from Infra
- RFD4-Proteina runs on an RTX 3060: protein design from $0.001 per design — AllThingsApx · 2026-10-27
- Nature Physics: reprogrammable refractive index enables arbitrary multimode wave control for ML — MarioKrenn6240 · 2026-10-27
- RTX Spark laptops impress analyst: 30B local model runs quiet with great battery life — Scobleizer · 2026-10-27
- Reflection AI's Beam-1.0 tops US open-weight models, hitting 88% of Qwen3.8-2.4T with 23B active params — ryanshrout · 2026-10-27
- Re-uploading a 239GB robot dataset moved only 2.6MB — inside a petabyte-scale data pipeline — mervenoyann · 2026-10-27
- Intel to acquire Classiq to build full-stack quantum computing platform — BenBajarin · 2026-10-27