Can I run gemma-4-E2B-it-GGUF on an RTX 5070?

Yes, just

Its BF16 file (9.31 GB) fits in the 10.8 GB an RTX 5070 can use, with room for ≈ 99K tokens of context.

Full analysis of gemma-4-E2B-it-GGUF Everything that runs on RTX 5070 Get the BF16 file on Hugging Face

ollama run hf.co/unsloth/gemma-4-E2B-it-GGUF:BF16

Files and context on RTX 5070

Each file of gemma-4-E2B-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 5070	Context (16-bit)	Context (8-bit)
BF16	9.31 GB	Tight	99K	128K
UD-Q8_K_XL	5.28 GB	Fits	128K	128K
Q8_0	5.05 GB	Fits	128K	128K
UD-Q6_K_XL	4.71 GB	Fits	128K	128K
Q6_K	4.50 GB	Fits	128K	128K
UD-Q5_K_XL	4.29 GB	Fits	128K	128K
Q5_K_M	3.36 GB	Fits	128K	128K
Q5_K_S	3.32 GB	Fits	128K	128K
UD-Q4_K_XL	3.18 GB	Fits	128K	128K
Q4_1	3.15 GB	Fits	128K	128K
Q4_K_M	3.11 GB	Fits	128K	128K
Q4_K_S	3.04 GB	Fits	128K	128K
Q4_0	3.04 GB	Fits	128K	128K
IQ4_NL	3.04 GB	Fits	128K	128K
IQ4_XS	2.98 GB	Fits	128K	128K
UD-Q3_K_XL	2.92 GB	Fits	128K	128K
Q3_K_M	2.54 GB	Fits	128K	128K
Q3_K_S	2.45 GB	Fits	128K	128K
UD-Q2_K_XL	2.40 GB	Fits	128K	128K
UD-IQ3_XXS	2.37 GB	Fits	128K	128K
UD-IQ2_M	2.29 GB	Fits	128K	128K

gemma-4-E2B-it-GGUF on other hardware

Popular models that run on RTX 5070

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.