RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek vl2 tiny run on the RTX 3080 10GB?

Yes. At 8K context the best fit is F16, using about 7.4 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~323 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.1 GB Fits1724
3-bit (Q3_K_M)2.4 GB Fits1323
4-bit (Q4_K_M)2.8 GB Fits1058
5-bit (Q5_K_M)3.1 GB Fits908
6-bit (Q6_K)3.5 GB Fits789
8-bit (Q8_0)4.2 GB Fits609
16-bit (F16/BF16)7.2 GB Fits323

• real GGUF file size. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.

More

deepseek vl2 tiny on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 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.