RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can SmolVLM Instruct run on the RTX 4070 Ti?

Yes. At 8K context the best fit is F16, using about 5.4 GB of the 11.4 GB usable on the RTX 4070 Ti. Estimated speed ceiling: ~139 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.0 GB Fits2.8 GB Fits598
3-bit (Q3_K_M)2.3 GB Fits3.0 GB Fits459
4-bit (Q4_K_M) •2.3 GB Fits3.0 GB Fits453
5-bit (Q5_K_M)2.7 GB Fits3.5 GB Fits315
6-bit (Q6_K)3.0 GB Fits3.7 GB Fits274
8-bit (Q8_0) •3.0 GB Fits3.8 GB Fits261
16-bit (F16/BF16) •4.6 GB Fits5.4 GB Fits139

• real GGUF file size from ggml-org/SmolVLM-Instruct-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

More

SmolVLM Instruct on every GPU and Mac · Every model that runs on the RTX 4070 Ti · Other models that fit 12 GB VRAM · Try other settings in the calculator

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