Container
OpenAI
GPT-OSS-120b-TurboThe GPT-OSS-120b-Turbo NIM container packages OpenAI's GPT-OSS-120b large language model, a sparse Mixture of Experts (MoE) architecture with 120B total parameters and 5.1B active parameters, as an NVIDIA NIM microservice.
Sign in to access this content
Sign in to see Related Collections for this ContainerSigning in will also allow download accessSign In