RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 3.2 1B run on the RTX 4060?

Yes. At 8K context the best fit is F16, using about 3.2 GB of the 7.6 GB usable on the RTX 4060. Estimated speed ceiling: ~110 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.4 GB Fits1.5 GB Fits2.3 GB Fits5.3 GB Fits408
3-bit (Q3_K_M) •1.5 GB Fits1.6 GB Fits2.4 GB Fits5.4 GB Fits338
4-bit (Q4_K_M) •1.7 GB Fits1.8 GB Fits2.5 GB Fits5.5 GB Fits285
5-bit (Q5_K_M) •1.8 GB Fits1.9 GB Fits2.7 GB Fits5.7 GB Fits249
6-bit (Q6_K) •1.9 GB Fits2.0 GB Fits2.8 GB Fits5.8 GB Fits220
8-bit (Q8_0) •2.3 GB Fits2.4 GB Fits3.1 GB Fits6.1 GB Fits170
16-bit (F16/BF16)3.1 GB Fits3.2 GB Fits3.9 GB Fits6.9 GB Tight110

• real GGUF file size from QuantFactory/Dolphin3.0-Llama3.2-1B-GGUF. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.

More

Llama 3.2 1B 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-3.2-1B), NVIDIA specs. Data as of 2026-11-17.