open-weights

An interactive guide for choosing local AI hardware and matching open-weights LLMs to specific builds. It offers budget-based build recommendations, a hardware picker, model-to-hardware compatibility, and a state-of-the-local-AI snapshot.

A from-scratch ~1B parameter language model on Hugging Face with open weights, open data, training details, and loading guidance. The page is unusually candid about capabilities, limits, and evaluation.

An open 45M-parameter agentic LLM for tiny devices, built for tool calling, device use, and structured extraction. It ships as a 14 MB binary and is positioned for phones, wearables, smart home devices, robots, and other low-RAM hardware.

A research page on how censorship and behavior transfer during model distillation, with published models, data, evaluation code, and a benchmark called LineageEval.

A field note about testing a coding agent fully offline on a laptop with Ollama and Qwen3.8 27B, including the setup, failure modes, and the workaround that made the project finish.