RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 3.2 3B run on the RTX 5070 Ti?

Yes. At 8K context the best fit is F16, using about 7.5 GB of the 15.2 GB usable on the RTX 5070 Ti. Estimated speed ceiling: ~139 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •2.5 GB Fits2.9 GB Fits5.5 GB Fits16.0 GB No600
3-bit (Q3_K_M) •2.8 GB Fits3.2 GB Fits5.9 GB Fits16.4 GB No483
4-bit (Q4_K_M) •3.2 GB Fits3.6 GB Fits6.2 GB Fits16.7 GB No400
5-bit (Q5_K_M) •3.5 GB Fits3.9 GB Fits6.6 GB Fits17.1 GB No346
6-bit (Q6_K) •3.8 GB Fits4.3 GB Fits6.9 GB Fits17.4 GB No302
8-bit (Q8_0) •4.7 GB Fits5.1 GB Fits7.7 GB Fits18.2 GB No233
16-bit (F16/BF16)7.1 GB Fits7.5 GB Fits10.1 GB Fits20.6 GB No139

• real GGUF file size from QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF. Speed is a bandwidth ceiling (896 GB/s), not a benchmark. Methodology.

More

Llama 3.2 3B on every GPU and Mac · Every model that runs on the RTX 5070 Ti · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (meta-llama/Llama-3.2-3B), NVIDIA specs. Data as of 2026-11-17.