Model Anatomy See what's inside open-weight AI models

Can I run gemma-4-31B-it on an RTX 3090?

Probably, at 4-bit

The published weights are too big, but a 4-bit version (about 17.6 GB) would fit, with room for ≈ 19K tokens of context. The site hasn't analyzed a GGUF of gemma-4-31B-it yet.

Full analysis of gemma-4-31B-it Everything that runs on RTX 3090

Files and context on RTX 3090

Each file of gemma-4-31B-it (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn RTX 3090 Context (16-bit)Context (8-bit)
As published62.5 GBDoesn't fit——
4-bit (estimate)17.6 GBTight19K43K

gemma-4-31B-it on other hardware

Popular models that run on RTX 3090

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.