Skip to content

Local AI on RTX 5090: which models run and how fast

Short answer

RTX 5090 has 32 GB of video memory, which holds 11 of Nightjar's eleven models entirely, the largest being Gemma 4 31B-it.

Video memory
32 GB
Models that fit fully
11 of 11
Largest that fits
Gemma 4 31B-it
This is our test card
no

Every model against this card

What the numbers here are and are not

The fit is arithmetic — a file size against a memory size, with about 1.1 GB added for context and runtime. The speeds elsewhere on this site were measured on RTX 3060 12 GB, Vulkan backend and nowhere else. Where a page says a figure was not measured, that is literal: we would rather leave a gap than publish an estimate that reads like a result.

Other ways people ask this

  • best local llm for rtx 5090
  • rtx 5090 llm tokens per second
  • I have a RTX 5090. Which local model should I run for browser AI?

Related