RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek moe 16b base run on the 2x RTX 3090?

Yes. At 8K context the best fit is F16, using about 32.8 GB of the 45.6 GB usable on the 2x RTX 3090. Estimated speed ceiling: ~165 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •7.7 GB Fits808
3-bit (Q3_K_M) •9.4 GB Fits639
4-bit (Q4_K_M) •11.6 GB Fits499
5-bit (Q5_K_M) •13.0 GB Fits437
6-bit (Q6_K) •15.1 GB Fits370
8-bit (Q8_0) •17.7 GB Fits311
16-bit (F16/BF16)32.0 GB Fits165

• real GGUF file size from mradermacher/deepseek-moe-16b-base-GGUF. Speed is a bandwidth ceiling (936 GB/s), not a benchmark. Methodology.

More

deepseek moe 16b base on every GPU and Mac · Every model that runs on the 2x RTX 3090 · Try other settings in the calculator

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