RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 3.2 11B Vision Instruct run on the RTX 4070 Ti?

Yes. At 8K context the best fit is Q6_K, using about 10.0 GB of the 11.4 GB usable on the RTX 4070 Ti. Estimated speed ceiling: ~58 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)5.0 GB Fits5.6 GB Fits9.4 GB Fits24.4 GB No126
3-bit (Q3_K_M)6.1 GB Fits6.8 GB Fits10.5 GB Tight25.5 GB No97
4-bit (Q4_K_M) •6.8 GB Fits7.4 GB Fits11.2 GB Tight26.2 GB No85
5-bit (Q5_K_M)8.4 GB Fits9.0 GB Fits12.7 GB No27.7 GB No66
6-bit (Q6_K)9.4 GB Fits10.0 GB Fits13.8 GB No28.8 GB No58
8-bit (Q8_0) •11.0 GB Tight11.6 GB No15.3 GB No30.3 GB No—
16-bit (F16/BF16) •19.5 GB No20.1 GB No23.9 GB No38.9 GB No—

• real GGUF file size from leafspark/Llama-3.2-11B-Vision-Instruct-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

More

Llama 3.2 11B Vision Instruct on every GPU and Mac · Every model that runs on the RTX 4070 Ti · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (meta-llama/Llama-3.2-11B-Vision-Instruct), NVIDIA specs. Data as of 2026-11-17.