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

Can I run gemma-4-12b-it-GGUF on an RTX 4090?

Yes

Its UD-Q8_K_XL file (13.6 GB) fits in the 21.6 GB an RTX 4090 can use, with room for ≈ 54K tokens of context.

Full analysis of gemma-4-12b-it-GGUF Everything that runs on RTX 4090 Get the UD-Q8_K_XL file on Hugging Face
ollama run hf.co/unsloth/gemma-4-12b-it-GGUF:UD-Q8_K_XL

Files and context on RTX 4090

Each file of gemma-4-12b-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 4090 Context (16-bit)Context (8-bit)
gemma-4-12b-it-BF1623.8 GBDoesn't fit——
UD-Q8_K_XL13.6 GBFits54K114K
gemma-4-12b-it-Q8_012.7 GBFits62K128K
UD-Q6_K_XL10.7 GBFits76K158K
Q6_K9.79 GBFits83K171K
UD-Q5_K_XL8.61 GBFits92K189K
Q5_K_M8.41 GBFits93K191K
Q5_K_S8.20 GBFits95K195K
Q4_17.40 GBFits101K207K
UD-Q4_K_XL7.37 GBFits101K207K
Q4_K_M7.12 GBFits103K211K
Q4_K_S6.76 GBFits106K216K
Q4_06.74 GBFits106K216K
IQ4_NL6.72 GBFits106K217K
IQ4_XS6.38 GBFits108K222K
UD-Q3_K_XL6.02 GBFits111K227K
Q3_K_M5.69 GBFits114K232K
Q3_K_S5.14 GBFits118K240K
UD-Q2_K_XL4.66 GBFits121K247K
UD-IQ3_XXS4.64 GBFits121K248K
UD-IQ2_M4.21 GBFits125K254K

gemma-4-12b-it-GGUF on other hardware

Popular models that run on RTX 4090

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.