Made With ML
Learn to build, deploy and iterate production ML apps
Runs huge models on small GPUs by streaming layers
A Python library that makes very large language models runnable on modest GPUs by loading model layers or experts on demand instead of fitting the whole model in video memory. It is for developers who need offline or air-gapped inference and can trade speed for access to large models.
The model weights stay on disk. AirLLM streams one layer or expert at a time into GPU memory, runs that portion, and then swaps in the next part, enabling large models to run on small graphics cards at very slow speeds.
Free: turn books into skills & the top 10 GitHub repos
Learn to build, deploy and iterate production ML apps
Pretrained foundation model for forecasting numeric time-series data
Bare-bones NumPy implementations of core ML algorithms
Real-time 3D scene reconstruction from camera frames
Command-line video downloader built to be wired into automated workflows
Open agent skills for documents, PDFs and office files