Skip to content
localmodel.run

Text model · gpt-oss

Can I run gpt-oss 120B? Pick your device.

gpt-oss 120B is a 117B MoE (5.1B active) model. At Q4_K_M the weights are ~59.03 GB; with KV cache and runtime overhead, budget ~62.4 GB. Select your hardware below to see the full compatibility breakdown.

Memory figures are estimates. See methodology.