RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 3.2 3B run on the RTX 4060?

Yes. At 8K context the best fit is Q8_0, using about 5.1 GB of the 7.6 GB usable on the RTX 4060. Estimated speed ceiling: ~71 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 No182
3-bit (Q3_K_M) •2.8 GB Fits3.2 GB Fits5.9 GB Fits16.4 GB No147
4-bit (Q4_K_M) •3.2 GB Fits3.6 GB Fits6.2 GB Fits16.7 GB No121
5-bit (Q5_K_M) •3.5 GB Fits3.9 GB Fits6.6 GB Fits17.1 GB No105
6-bit (Q6_K) •3.8 GB Fits4.3 GB Fits6.9 GB Tight17.4 GB No92
8-bit (Q8_0) •4.7 GB Fits5.1 GB Fits7.7 GB No18.2 GB No71
16-bit (F16/BF16)7.1 GB Tight7.5 GB Tight10.1 GB No20.6 GB No42

• real GGUF file size from QuantFactory/OneLLM-Doey-V1-Llama-3.2-3B-GGUF. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.

More

Llama 3.2 3B on every GPU and Mac · Every model that runs on the RTX 4060 · Other models that fit 8 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.