RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM2 1.7B run on the RTX 3080 12GB?

Yes. At 8K context the best fit is F16, using about 5.2 GB of the 11.4 GB usable on the RTX 3080 12GB. Estimated speed ceiling: ~266 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.8 GB Fits2.6 GB Fits1421
3-bit (Q3_K_M)2.0 GB Fits2.8 GB Fits1090
4-bit (Q4_K_M) •2.3 GB Fits3.0 GB Fits844
5-bit (Q5_K_M)2.4 GB Fits3.1 GB Fits748
6-bit (Q6_K)2.6 GB Fits3.3 GB Fits650
8-bit (Q8_0) •3.0 GB Fits3.7 GB Fits492
16-bit (F16/BF16)4.4 GB Fits5.2 GB Fits266

• real GGUF file size from namindu94/SinhalaLLM-1.7B. Speed is a bandwidth ceiling (912 GB/s), not a benchmark. Methodology.

More

SmolLM2 1.7B on every GPU and Mac · Every model that runs on the RTX 3080 12GB · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (HuggingFaceTB/SmolLM2-1.7B), NVIDIA specs. Data as of 2026-11-17.