{
  "id": "gpt-oss-120b",
  "name": "gpt-oss-120b",
  "developer": "OpenAI",
  "exact_model_id": "openai/gpt-oss-120b",
  "verified_at": "2026-09-27",
  "evidence_level": "source-verified",
  "access": {
    "label": "Direct download",
    "gated": false
  },
  "license": {
    "name": "Apache 2.0 + usage policy",
    "commercial_use": "Broad commercial use under Apache 2.0, subject to the usage policy.",
    "eu_note": "No explicit EU territorial restriction identified in the reviewed publisher materials."
  },
  "architecture": {
    "parameters": "120B class",
    "type": "Mixture-of-Experts reasoning model",
    "context": "See current model card",
    "modalities": "Text → text"
  },
  "runtimes": [
    "Transformers",
    "vLLM",
    "Ollama",
    "llama.cpp"
  ],
  "hardware_note": "OpenAI states the 120B model can run efficiently on a single 80 GB GPU.",
  "primary_source": "https://openai.com/index/introducing-gpt-oss/",
  "third_party_runtime_evidence": [],
  "reference_page": "https://openweightmodels.eu/model-gpt-oss-120b.html",
  "owm_view": "gpt-oss-120b is the more infrastructure-oriented member of OpenAI’s open-weight family. OWM sees it as strategically important because it brings a much larger reasoning model into a deployment envelope that OpenAI says can fit on a single 80 GB GPU, while still preserving the operator’s ability to choose the serving stack.",
  "seo_reference_verified_at": "2026-09-27",
  "change_history": "https://openweightmodels.eu/change-gpt-oss-120b.json"
}