Conversation models that run on 128 GB

613 models with published weights that fit in 128 GB — a large Mac or a server card. Counted at four-bit quantisation, weights only, leaving the machine about a third of its memory and a gigabyte for context: room for roughly 136 billion parameters. A mixture of experts is counted in full, because it is held in full even though only a few experts compute. 613 in all, a hundred to a page; this is page 3 of 7.

A large Mac or a server card. This is where the biggest openly published models come within reach — and where the distinction between total and active parameters starts to decide everything, because a mixture of experts computes with a fraction of itself and must still be held whole.

Models that answer in prose across whatever subject you put to them. This is the largest category and the least differentiated: most of them are competent at most things, so the choice usually comes down to price, context length and how the maker behaves about availability. Look at what a model costs per million tokens in and out — the output rate is often four or five times the input rate, and it is the one that decides your bill.

Wider

Conversation models Models that run on 128 GB