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

Can I run gemma-4-26B-A4B-it-AWQ-4bit on an RTX 3090?

Yes

Its published weights (17.2 GB) fit in the 21.6 GB an RTX 3090 can use, with room for ≈ 100K tokens of context.

Full analysis of gemma-4-26B-A4B-it-AWQ-4bit Everything that runs on RTX 3090 Get the weights on Hugging Face
hf download cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit

Files and context on RTX 3090

Each file of gemma-4-26B-A4B-it-AWQ-4bit (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 published17.2 GBFits100K205K
4-bit (estimate)14.5 GBFits164K256K

gemma-4-26B-A4B-it-AWQ-4bit 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.