Local AI use cases with 7B-13B models
Small open-weight language models in the 7 to 13 billion parameter range. Quantized, they run on a single consumer GPU or a decent CPU, which makes them the workhorse for narrow, repeatable local tasks.
Rebel BitesExtracting clean data from old SEC filings with small models
7B-13B models running locally turn wordy 1990s SEC text filings into structured tables, about 97% accurate on a random sample. Lots of tiny prompts, because tokens are free.