RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek vl2 tiny run on the RTX 4060?

Yes. At 8K context the best fit is Q8_0, using about 4.5 GB of the 7.6 GB usable on the RTX 4060. Estimated speed ceiling: ~218 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.1 GB Fits617
3-bit (Q3_K_M)2.4 GB Fits473
4-bit (Q4_K_M)2.8 GB Fits379
5-bit (Q5_K_M)3.1 GB Fits325
6-bit (Q6_K)3.5 GB Fits282
8-bit (Q8_0)4.2 GB Fits218
16-bit (F16/BF16)7.2 GB Tight116

• real GGUF file size. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.

More

deepseek vl2 tiny on every GPU and Mac · Every model that runs on the RTX 4060 · 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.