RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM 1.7B run on the RTX 4060?

Yes. At 8K context the best fit is F16, using about 5.2 GB of the 7.6 GB usable on the RTX 4060. Estimated speed ceiling: ~79 tokens/sec.

Memory by quant and context

QuantMax tok/s (est., 8K)
2-bit (Q2_K) •403
3-bit (Q3_K_M) •316
4-bit (Q4_K_M) •258
5-bit (Q5_K_M) •222
6-bit (Q6_K) •193
8-bit (Q8_0) •149
16-bit (F16/BF16) •79

• real GGUF file size from mradermacher/SmolLM-1.7B-GGUF. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.

More

SmolLM 1.7B 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 (HuggingFaceTB/SmolLM-1.7B), NVIDIA specs. Data as of 2026-11-17.