Can I run gemma-4-12b-it-GGUF on an RTX 5090?

Yes, just

Its gemma-4-12b-it-BF16 file (23.8 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 32K tokens of context.

Full analysis of gemma-4-12b-it-GGUF Everything that runs on RTX 5090 Get the gemma-4-12b-it-BF16 file on Hugging Face

ollama run hf.co/unsloth/gemma-4-12b-it-GGUF

Files and context on RTX 5090

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.

File	Size	On RTX 5090	Context (16-bit)	Context (8-bit)
gemma-4-12b-it-BF16	23.8 GB	Tight	32K	69K
UD-Q8_K_XL	13.6 GB	Fits	108K	221K
gemma-4-12b-it-Q8_0	12.7 GB	Fits	115K	235K
UD-Q6_K_XL	10.7 GB	Fits	130K	256K
Q6_K	9.79 GB	Fits	137K	256K
UD-Q5_K_XL	8.61 GB	Fits	145K	256K
Q5_K_M	8.41 GB	Fits	147K	256K
Q5_K_S	8.20 GB	Fits	148K	256K
Q4_1	7.40 GB	Fits	154K	256K
UD-Q4_K_XL	7.37 GB	Fits	155K	256K
Q4_K_M	7.12 GB	Fits	157K	256K
Q4_K_S	6.76 GB	Fits	159K	256K
Q4_0	6.74 GB	Fits	159K	256K
IQ4_NL	6.72 GB	Fits	160K	256K
IQ4_XS	6.38 GB	Fits	162K	256K
UD-Q3_K_XL	6.02 GB	Fits	165K	256K
Q3_K_M	5.69 GB	Fits	167K	256K
Q3_K_S	5.14 GB	Fits	171K	256K
UD-Q2_K_XL	4.66 GB	Fits	175K	256K
UD-IQ3_XXS	4.64 GB	Fits	175K	256K
UD-IQ2_M	4.21 GB	Fits	178K	256K

gemma-4-12b-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.