Embeddings models that run on 24 GB

59 models with published weights that fit in 24 GB — a 24 GB card, or a Mac with 24. Counted at four-bit quantisation, weights only, leaving the machine about a third of its memory and a gigabyte for context: room for roughly 24 billion parameters. A mixture of experts is counted in full, because it is held in full even though only a few experts compute.

A 24 GB graphics card or a Mac configured with 24. This is the first size where the well-regarded mid-weight models — the twenty-something billion parameter class — run comfortably, and where a local model starts to be a real alternative to an API for daily work rather than a demonstration.

Models that turn text into a vector so it can be searched by meaning rather than by words. They are cheap — usually cents per million tokens, and often priced for input only, since nothing comes back but numbers. Two things decide the choice: the dimension of the vector, which sets what your database will cost to hold, and whether the model was trained for your language. Changing model later means re-embedding everything you have.

Wider

Embeddings models Models that run on 24 GB