RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM3 3B Base run on the RTX 3060 12GB?

Yes. At 8K context the best fit is F16, using about 6.9 GB of the 11.4 GB usable on the RTX 3060 12GB. Estimated speed ceiling: ~59 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •2.1 GB Fits2.4 GB Fits4.1 GB Fits287
3-bit (Q3_K_M) •2.4 GB Fits2.7 GB Fits4.4 GB Fits229
4-bit (Q4_K_M) •2.7 GB Fits3.0 GB Fits4.7 GB Fits188
5-bit (Q5_K_M) •3.0 GB Fits3.3 GB Fits5.0 GB Fits163
6-bit (Q6_K) •3.3 GB Fits3.6 GB Fits5.3 GB Fits142
8-bit (Q8_0)4.0 GB Fits4.3 GB Fits5.9 GB Fits110
16-bit (F16/BF16)6.7 GB Fits6.9 GB Fits8.6 GB Fits59

• real GGUF file size from mradermacher/SmolLM3-3B-Base-i1-GGUF. Speed is a bandwidth ceiling (360 GB/s), not a benchmark. Methodology.

More

SmolLM3 3B Base on every GPU and Mac · Every model that runs on the RTX 3060 12GB · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (HuggingFaceTB/SmolLM3-3B-Base), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.