Skip to content

Text model · DeepSeek-V4

Can I run DeepSeek-V4-Flash? Pick your device.

DeepSeek-V4-Flash is a 284B MoE (13B active) model. At Q4_K_M the weights are ~174.87 GB; with KV cache and runtime overhead, budget ~179.7 GB. Select your hardware below to see the full compatibility breakdown.

Memory figures are estimates. See methodology.