RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek V3.2 Exp run on the RTX 4070 Super?

No. Even at 2-bit with 8K context, DeepSeek V3.2 Exp needs about 241 GB, more than the 11.4 GB usable on the RTX 4070 Super.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)240 GB No241 GB No243 GB No251 GB No—
3-bit (Q3_K_M)313 GB No313 GB No315 GB No323 GB No—
4-bit (Q4_K_M)391 GB No391 GB No393 GB No401 GB No—
5-bit (Q5_K_M)456 GB No456 GB No458 GB No466 GB No—
6-bit (Q6_K)524 GB No525 GB No527 GB No535 GB No—
8-bit (Q8_0)679 GB No680 GB No681 GB No689 GB No—
16-bit (F16/BF16)1278 GB No1278 GB No1280 GB No1288 GB No—

• real GGUF file size. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

Hardware that does fit it

Mac M3 Ultra 512GB

More

DeepSeek V3.2 Exp on every GPU and Mac · Every model that runs on the RTX 4070 Super · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/DeepSeek-V3.2-Exp), NVIDIA specs. Data as of 2026-11-17.