Local AI use cases with DeepSeek
DeepSeek publishes open-weight models, including the R1 reasoning family, in sizes that can run locally through Ollama or llama.cpp.
14 months local-first: what still breaks
An honest report from a three-machine home lab. Local handles about 85% of tasks, but four kinds of work still fail, and that cut cloud spend from $187 to about $25 a month.