RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolLM2 1.7B Instruct run on the RTX 4070?

Yes. At 8K context the best fit is F16, using about 5.2 GB of the 11.4 GB usable on the RTX 4070. Estimated speed ceiling: ~147 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.9 GB Fits2.6 GB Fits747
3-bit (Q3_K_M) •2.0 GB Fits2.8 GB Fits586
4-bit (Q4_K_M) •2.2 GB Fits3.0 GB Fits477
5-bit (Q5_K_M) •2.4 GB Fits3.1 GB Fits411
6-bit (Q6_K) •2.6 GB Fits3.3 GB Fits358
8-bit (Q8_0) •2.9 GB Fits3.7 GB Fits277
16-bit (F16/BF16) •4.4 GB Fits5.2 GB Fits147

• real GGUF file size from unsloth/SmolLM2-1.7B-Instruct-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

More

SmolLM2 1.7B Instruct on every GPU and Mac · Every model that runs on the RTX 4070 · Other models that fit 12 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.