Skip to content

Text model · Kimi

KI Can I run Kimi K2 Instruct? Pick your device.

Kimi K2 Instruct is a 1000B MoE (32B active) model. At Q4_K_M the weights are ~578.15 GB; with KV cache and runtime overhead, budget ~586.6 GB. Select your hardware below to see the full compatibility breakdown.

Memory figures are estimates. See methodology.