RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek moe 16b base run on the RTX 3070?

No. Even at 2-bit with 8K context, deepseek moe 16b base needs about 8.6 GB, more than the 7.6 GB usable on the RTX 3070.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •7.7 GB No—
3-bit (Q3_K_M) •9.4 GB No—
4-bit (Q4_K_M) •11.6 GB No—
5-bit (Q5_K_M) •13.0 GB No—
6-bit (Q6_K) •15.1 GB No—
8-bit (Q8_0) •17.7 GB No—
16-bit (F16/BF16)32.0 GB No—

• real GGUF file size from mradermacher/deepseek-moe-16b-base-GGUF. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.

Hardware that does fit it

RTX 3080 10GBRTX 3060 12GBRTX 3080 12GBRTX 4070RTX 4070 SuperRTX 4070 Ti

More

deepseek moe 16b base on every GPU and Mac · Every model that runs on the RTX 3070 · Other models that fit 8 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/deepseek-moe-16b-base), NVIDIA specs. Data as of 2026-11-17.