RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek vl2 tiny run on the RTX 5060?

Yes. At 8K context the best fit is Q8_0, using about 4.5 GB of the 7.6 GB usable on the RTX 5060. Estimated speed ceiling: ~359 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.1 GB Fits1016
3-bit (Q3_K_M)2.4 GB Fits780
4-bit (Q4_K_M)2.8 GB Fits624
5-bit (Q5_K_M)3.1 GB Fits535
6-bit (Q6_K)3.5 GB Fits465
8-bit (Q8_0)4.2 GB Fits359
16-bit (F16/BF16)7.2 GB Tight191

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

More

deepseek vl2 tiny on every GPU and Mac · Every model that runs on the RTX 5060 · Other models that fit 8 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/deepseek-vl2-tiny), NVIDIA specs. Data as of 2026-11-17.