RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolVLM Instruct run on the RTX 4070 Ti Super?

Yes. At 8K context the best fit is F16, using about 5.4 GB of the 15.2 GB usable on the RTX 4070 Ti Super. Estimated speed ceiling: ~185 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.0 GB Fits2.8 GB Fits798
3-bit (Q3_K_M)2.3 GB Fits3.0 GB Fits612
4-bit (Q4_K_M) •2.3 GB Fits3.0 GB Fits604
5-bit (Q5_K_M)2.7 GB Fits3.5 GB Fits420
6-bit (Q6_K)3.0 GB Fits3.7 GB Fits365
8-bit (Q8_0) •3.0 GB Fits3.8 GB Fits349
16-bit (F16/BF16) •4.6 GB Fits5.4 GB Fits185

• real GGUF file size from ggml-org/SmolVLM-Instruct-GGUF. Speed is a bandwidth ceiling (672 GB/s), not a benchmark. Methodology.

More

SmolVLM Instruct on every GPU and Mac · Every model that runs on the RTX 4070 Ti Super · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (HuggingFaceTB/SmolVLM-Instruct), NVIDIA specs. Data as of 2026-11-17.