gpt-oss-120b
Open weightsOpen weightsText120B parametersReasoning
gpt-oss family model by OpenAI.
About the gpt-oss family
OpenAI's open-weight MoE models (20B and 120B) released under Apache 2.0 — the company's first open weights since GPT-2. Strong reasoning for their size and runnable on consumer hardware (20B) or a single big GPU (120B).
All gpt-oss modelsHow this one is configured
This configuration runs in reasoning mode (thinks step-by-step before answering); ~120B parameters.
Also runs at: low · high effort
Effort controls how long the model thinks before answering — higher effort usually means better answers on hard problems, at the cost of speed and money. Same model underneath, so they share this page.