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

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

Yes, just

Its UD-Q8_K_XL file (27.6 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 9K tokens of context.

Full analysis of gemma-4-26B-A4B-it-GGUF Everything that runs on RTX 5090 Get the UD-Q8_K_XL file on Hugging Face
ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q8_K_XL

Files and context on RTX 5090

Each file of gemma-4-26B-A4B-it-GGUF (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)
BF1650.5 GBDoesn't fit——
UD-Q8_K_XL27.6 GBTight9K23K
Q8_026.9 GBTight18K41K
UD-Q6_K_XL23.3 GBTight61K126K
UD-Q6_K23.2 GBTight62K129K
UD-Q5_K_XL21.2 GBFits85K176K
UD-Q5_K_M21.2 GBFits86K177K
UD-Q5_K_S18.9 GBFits114K232K
UD-Q4_K_XL17.0 GBFits136K256K
UD-Q4_K_M16.9 GBFits136K256K
MXFP4_MOE16.6 GBFits141K256K
UD-Q4_K_S16.5 GBFits142K256K
UD-IQ4_NL13.6 GBFits176K256K
UD-IQ4_XS13.6 GBFits176K256K
UD-Q3_K_XL12.9 GBFits184K256K
UD-Q3_K_M12.7 GBFits187K256K
UD-IQ3_XXS11.4 GBFits202K256K
UD-IQ3_S11.3 GBFits204K256K
UD-Q2_K_XL10.5 GBFits213K256K
UD-IQ2_M10.0 GBFits219K256K
UD-IQ2_XXS9.92 GBFits220K256K

gemma-4-26B-A4B-it-GGUF 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.