RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can gemma 3 12b it run on the RTX 4070?

Yes. At 8K context the best fit is Q5_K_M, using about 9.6 GB of the 11.4 GB usable on the RTX 4070. Estimated speed ceiling: ~60 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •5.9 GB Fits6.2 GB Fits7.7 GB Fits13.7 GB No106
3-bit (Q3_K_M) •7.1 GB Fits7.3 GB Fits8.8 GB Fits14.8 GB No84
4-bit (Q4_K_M) •8.3 GB Fits8.5 GB Fits10.0 GB Fits16.0 GB No69
5-bit (Q5_K_M) •9.3 GB Fits9.6 GB Fits11.1 GB Tight17.1 GB No60
6-bit (Q6_K) •10.5 GB Tight10.7 GB Tight12.2 GB No18.2 GB No52
8-bit (Q8_0) •13.1 GB No13.4 GB No14.9 GB No20.9 GB No—
16-bit (F16/BF16) •23.4 GB No23.6 GB No25.1 GB No31.1 GB No—

• real GGUF file size from unsloth/gemma-3-12b-it-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

More

gemma 3 12b it on every GPU and Mac · Every model that runs on the RTX 4070 · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (google/gemma-3-12b-it), NVIDIA specs. Data as of 2026-11-17.