RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM2 1.7B Instruct 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

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.9 GB Fits2.6 GB Fits403
3-bit (Q3_K_M) •2.0 GB Fits2.8 GB Fits316
4-bit (Q4_K_M) •2.2 GB Fits3.0 GB Fits258
5-bit (Q5_K_M) •2.4 GB Fits3.1 GB Fits222
6-bit (Q6_K) •2.6 GB Fits3.3 GB Fits193
8-bit (Q8_0) •2.9 GB Fits3.7 GB Fits149
16-bit (F16/BF16) •4.4 GB Fits5.2 GB Fits79

• real GGUF file size from unsloth/SmolLM2-1.7B-Instruct-GGUF. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.

More

SmolLM2 1.7B Instruct 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/SmolLM2-1.7B-Instruct), NVIDIA specs. Data as of 2026-11-17.