Reasoning weights people can run themselves.
OpenAI released gpt-oss-120b and gpt-oss-20b as Apache-2.0 open-weight reasoning models, with downloadable weights and reference implementations for local deployment.
- Maturity
- Deployed, stage 4 of 4
- Support
- 1 source · institution
- Evidence detail
- How we know ↓
Some people and organizations need to customize a model or keep inference on infrastructure they control, but frontier-style reasoning has often required a hosted service.
Running a capable reasoning model locally commonly required expensive hardware or gave users little ability to modify deployment.
Two mixture-of-experts language models designed for tool use, structured outputs, and adjustable reasoning effort.
What was shown, and what wasn’t
Shown
OpenAI states that the 120b model can run within 80 GB of memory and the 20b model within 16 GB; the weights are downloadable from Hugging Face. It reports benchmark results in which 120b approaches o4-mini on core reasoning and 20b is similar to o3-mini on common benchmarks.
Not shown · limits
- These are open-weight releases, not a complete public release of training data or all model-development details.
- OpenAI's performance and safety results are source-vendor evaluations, not independent evidence of benefit in a specific setting.
- Open weights can be fine-tuned for harmful purposes; OpenAI explicitly says the models are not intended for medical diagnosis or treatment.
- A stated 16 GB memory requirement does not guarantee equally accessible hardware, energy use, or easy setup.
Bright editorial interpretation
Local or self-hosted use can offer people more deployment choice, including privacy-sensitive settings and adaptation to specialized work.
Still open
How well do locally deployed versions perform in real, safety-critical workflows?
What accessibility and operating-cost barriers remain for people without suitable hardware?
How should harms from malicious fine-tuning be measured and mitigated over time?
How we know1 source · checked 2026-09-07 · no corrections
- Maturity
- Deployed
- Source published
- 2025-08-05
- Captured
- 2026-09-07
- Last source review
- 2026-09-07
- Editorial method
- AI-assisted source review
Bright compared this account with the linked original and supporting sources and kept reported, budgeted, projected, and observed claims distinct. Bright did not independently audit the underlying records.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Revision & correction history
2026-09-07 · Local or self-hosted use can offer people more deployment choice, including privacy-sensitive settings and adaptation to specialized work.
No corrections recorded.