gpt-oss-120b
OpenAI · gpt-oss
Larger gpt-oss model for users evaluating high-capacity open-weight deployments.
Best for
Teams evaluating high-capacity local, self-hosted, or developer-controlled model deployments.
Tradeoffs
Larger open-weight models require careful license review, serving support, hardware planning, and evaluation on your own workloads.
Local hardware notes
Expect server-class requirements for full-weight deployment; use hosted or quantized options where available.
Local workflow notes
Best evaluated with the exact release, runtime support, and hardware profile available to your team.
Local runtimes: vLLM where supported, Transformers where supported
Platforms: Self-hosted servers, Linux
Availability and license note
Frontier 2026 model availability, licenses, context windows, and serving support can change quickly. Verify the official model card, provider docs, and license before using this model in production or commercial workflows.