RigValue UK

Best GPU for 27B to 35B AI models

The "B" in a model's name is how many billions of settings it has. Bigger models give better answers but need more memory: to run 27B to 35B models fully on the card (or a Mac's shared memory) you need at least 20 GB. Below is every option we track with that much memory and a verified UK price, ranked by value where there are enough real speed tests. Prices refresh every morning.

Best value for 27B to 35B models

RTX 5090 32GB: £4,301 used, 70.9 tokens per second on 27B to 35B models (from 75 tests), 32 GB of memory.

A token is roughly ¾ of a word, so that is about 53 words per second.

Cheapest way in

The cheapest option we track with enough memory for 27B to 35B models is the RX 7900 XT 20GB at £565 used (20 GB).

Ranked by value

Price divided by speed on 27B to 35B models. Lower £ per speed is better.

Hardware for 27B to 35B models ranked by £ per token per second
RankOptionUK priceSpeed£ per speedMemory
#1RTX 5090 32GB£4,301 used70.9 tok/s from 75 tests£60.6632 GB

Also fits, not ranked yet

Other model sizes: 7B to 9B models · 12B to 14B models · 70B and bigger models · By budget: under £300 · under £500 · under £1,000 · under £2,000 · All cards · Beginner's guide · How we rank

Weekly UK value moves, by email

Price drops, new benchmark results, best buys under £500 / £1,000 / £2,000.

Check your inbox to confirm: we use double opt-in, so you're only added after clicking the link in the confirmation email. Free; unsubscribe any time. Sent via Mailchimp (see their privacy notice).