Crawling the web models that run on 256 GB
2 models with published weights that fit in 256 GB — a Mac Studio with 256. Counted at four-bit quantisation, weights only, leaving the machine about a third of its memory and a gigabyte for context: room for roughly 274 billion parameters. A mixture of experts is counted in full, because it is held in full even though only a few experts compute.
A Mac Studio at the top of its configuration, or a serious machine. Almost everything openly published fits, including the large mixtures of experts. At this point the constraint is no longer whether the model loads but whether it generates fast enough to be worth waiting for.
Tools that fetch pages and hand them back as something a model can read: rendered HTML, markdown, a screenshot, a whole site map. Priced per page or per session. The differences that matter are whether JavaScript is executed, what happens at a login or a bot check, and how gracefully the thing fails on a site that does not want to be read.
- xlm-roberta-largeFacebook AI community0.6B≈0.4 GB at 4-bit
- xlm-roberta-baseFacebook AI community0.3B≈0.2 GB at 4-bit