Text model · Qwen3

Can I run Qwen3 30B-A3B? Pick your device.

Qwen3 30B-A3B is a 30.5B MoE (3.3B active) model. At Q4_K_M the weights are ~18.6 GB; with KV cache and runtime overhead, budget ~20.7 GB. Select your hardware below to see the full compatibility breakdown.

Memory figures are estimates. See methodology.