RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can gemma 4 31B it run on the RTX 3090 Ti?

Yes. At 8K context the best fit is Q4_K_M, using about 20.0 GB of the 22.8 GB usable on the RTX 3090 Ti. Estimated speed ceiling: ~55 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)13.2 GB Fits13.9 GB Fits17.6 GB Fits32.6 GB No86
3-bit (Q3_K_M) •16.0 GB Fits16.7 GB Fits20.4 GB Fits35.4 GB No68
4-bit (Q4_K_M) •19.4 GB Fits20.0 GB Fits23.7 GB No38.7 GB No55
5-bit (Q5_K_M) •22.5 GB Tight23.1 GB No26.9 GB No41.9 GB No—
6-bit (Q6_K) •25.8 GB No26.4 GB No30.2 GB No45.2 GB No—
8-bit (Q8_0) •32.7 GB No33.3 GB No37.1 GB No52.1 GB No—
16-bit (F16/BF16) •59.5 GB No60.1 GB No63.9 GB No78.9 GB No—

• real GGUF file size from unsloth/gemma-4-31B-it-GGUF. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.

More

gemma 4 31B it on every GPU and Mac · Every model that runs on the RTX 3090 Ti · Other models that fit 24 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (google/gemma-4-31B-it), NVIDIA specs. Data as of 2026-11-17.