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

Can I run gemma-4-26B-A4B-it-FP8-dynamic on an RTX 5090?

Probably, at 4-bit

The published weights are too big, but a 4-bit version (about 14.9 GB) would fit, with room for ≈ 256K tokens of context. The site hasn't analyzed a GGUF of gemma-4-26B-A4B-it-FP8-dynamic yet.

Full analysis of gemma-4-26B-A4B-it-FP8-dynamic Everything that runs on RTX 5090

Files and context on RTX 5090

Each file of gemma-4-26B-A4B-it-FP8-dynamic (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 5090 Context (16-bit)Context (8-bit)
As published28.6 GBDoesn't fit6573K
4-bit (estimate)14.9 GBFits256K256K

gemma-4-26B-A4B-it-FP8-dynamic on other hardware

Popular models that run on RTX 5090

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.