RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can FastVLM 0.5B run on the RTX 3060 Ti?

Yes. At 8K context the best fit is F16, using about 2.2 GB of the 7.6 GB usable on the RTX 3060 Ti. Estimated speed ceiling: ~295 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.0 GB Fits1.0 GB Fits1.3 GB Fits1574
3-bit (Q3_K_M)1.1 GB Fits1.1 GB Fits1.4 GB Fits1208
4-bit (Q4_K_M)1.2 GB Fits1.2 GB Fits1.5 GB Fits966
5-bit (Q5_K_M)1.2 GB Fits1.3 GB Fits1.6 GB Fits829
6-bit (Q6_K)1.3 GB Fits1.4 GB Fits1.6 GB Fits720
8-bit (Q8_0)1.5 GB Fits1.5 GB Fits1.8 GB Fits556
16-bit (F16/BF16)2.2 GB Fits2.2 GB Fits2.5 GB Fits295

• real GGUF file size. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.

More

FastVLM 0.5B on every GPU and Mac · Every model that runs on the RTX 3060 Ti · Other models that fit 8 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (apple/FastVLM-0.5B), NVIDIA specs. Data as of 2026-11-17.