RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek V3 run on the 2x RTX 4090?

No. Even at 2-bit with 8K context, DeepSeek V3 needs about 240 GB, more than the 45.6 GB usable on the 2x RTX 4090.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)240 GB No240 GB No242 GB No248 GB No—
3-bit (Q3_K_M) •298 GB No298 GB No300 GB No307 GB No—
4-bit (Q4_K_M) •378 GB No378 GB No379 GB No386 GB No—
5-bit (Q5_K_M) •444 GB No444 GB No446 GB No452 GB No—
6-bit (Q6_K) •514 GB No514 GB No516 GB No522 GB No—
8-bit (Q8_0) •665 GB No665 GB No667 GB No674 GB No—
16-bit (F16/BF16)1276 GB No1276 GB No1278 GB No1284 GB No—

• real GGUF file size from unsloth/DeepSeek-V3-GGUF. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.

Hardware that does fit it

Mac M3 Ultra 512GB

More

DeepSeek V3 on every GPU and Mac · Every model that runs on the 2x RTX 4090 · Try other settings in the calculator

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