Support · OpenAI gpt-oss
Will it last?
Ownership levelSubstantialnone·limited·partial·substantial·fullAnalytical input B ยท 78.8/100
This page is a projection of the one entry record, the Transparency factor that Support covers. The full verdict is set by all four factors together, floor-weighted so the weakest caps the whole.
Which domain expands which factor
- AssessUse & modify + Transparency
- ImplementData control + Reliability
- UseReliability
- SupportTransparency
Common problems & fixes
Common pitfalls, not an exhaustive catalogue.
Malformed or empty output, or leaked reasoning, usually means the harmony format is not
applied. Build prompts with the openai/harmony renderer and never display the raw reasoning
channel to users.
Model load or dtype errors: MXFP4 needs a recent runtime. Upgrade transformers, vLLM or
llama.cpp and load with torch_dtype="auto" so the library picks MXFP4.
A GGUF that loads in one runtime but not another: quant type codes have differed between
llama.cpp and Ollama for gpt-oss. Use a GGUF built for the specific runtime and verify it.
Out-of-memory: serve the 20b, keep native MXFP4, or reduce max context to shrink the KV cache.
The 120b needs an 80GB GPU.
Non-reproducible results and silent updates come from floating on main. Pin an exact
Hugging Face revision and verify checksums.
Versions, changelog & cadence
gpt-oss launched in August 2025 as a single release of two sizes (gpt-oss-120b and
gpt-oss-20b), not a rolling semantic-version stream. Versions are tracked as immutable
Hugging Face revisions on the openai org, so the revision hash is the changelog anchor. Pin
it, and diff against a newer revision if OpenAI republishes. The model card and arXiv report
document what shipped. OpenAI's separate gpt-oss-safeguard classifier family is a different
release, not a new gpt-oss version.
Code-level issues go to GitHub: openai/gpt-oss (reference implementations, serving and
fine-tuning guidance) and openai/harmony (the response-format renderer) (ev-github). The
OpenAI Cookbook has guides for gpt-oss deployment and harmony usage. Usage questions go to the
Hugging Face model discussion tabs on the openai org (ev-hf-openai).
There is no paid support tier for the open weights, only community and maintainer support
around an open release.
Tracked known issues
These come from model-card caveats, not a formal issue tracker, hence partial. Raw
chain-of-thought is unsafe to display, because it is deliberately unaligned and can contain
incorrect or harmful content. Safety tuning is removable on open weights, the concern behind
OpenAI's malicious-fine-tuning study, so any derivative needs re-evaluation. The hallucination
profile is standard for the class, since strong reasoning does not eliminate confabulation.
Behaviour is English-centric, and other-language quality is unverified.
How this scores
The ownership factor this domain covers, drawn from the one entry record.
2
TransparencyDo you know what it is: weights, training, behaviour, and legible terms?
ModerateWeights are open and inspectable, and OpenAI published a safety report whose worst-case malicious-fine-tuning methodology was independently reviewed by METR. Training data and pre-training code are closed, so the weights can be adapted but not reproduced, and how the model was made cannot be seen.
How this scores (AOI sub-dimensions)
Provenance4/5how well we can trace and verify what went into the modelVerified openai org on Hugging Face, safetensors-only distribution with checksums, a clear canonical source and no malicious-checkpoint incident on the canonical org (checklist ~6/8).
Governance4/5how accountable and well-documented the publisher isOpenAI is a reputable, legally accountable US publisher with a detailed model card and arXiv report, a public reference repository, a documented Preparedness-Framework process and coordinated external safety testing.
What this means for adoptionYou substantially own gpt-oss: ungated Apache-2.0 weights that you run, modify and self-host, governed by a two-sentence usage policy (obey applicable law) that is about as light as an open-weight AUP gets. The safety posture is a differentiator: a published worst-case malicious-fine-tuning study whose methodology METR independently reviewed, with OpenAI at least partially addressing each of METR's six high-urgency items. Transparency holds ownership below full: training data and pre-training code are closed, so the weights can be adapted but not reproduced. Adopt it for general open-weight deployment, building to the harmony response format it requires and adding standard input/output guardrails for customer-facing use.
Sources
The same evidence records as the entry sheet. Read means the text was verified; unverified means it is known to exist but not yet read.
Vendor announcementunverified2026-07-25
OpenAI introduces gpt-oss-120b and gpt-oss-20b as open-weight reasoning models under Apache-2.0 with configurable reasoning effort, native agentic tool use and structured outputs, running on 80GB / 16GB hardware.
Technical_reportread2026-07-25
The gpt-oss-120b & gpt-oss-20b Model Card (arXiv 2508.10925) describes two open-weight reasoning models on an efficient mixture-of-expert transformer architecture, trained with large-scale distillation and reinforcement learning.
Model cardread2026-11-19
gpt-oss weights are hosted on the verified openai organisation on Hugging Face as safetensors under Apache-2.0 with a 128K context window.
Licenceread2026-07-25
The gpt-oss LICENSE is a standard Apache License 2.0 (January 2004) boilerplate with the copyright line left as a template placeholder and no bespoke restrictions in the file itself: unconditional commercial use.
Terms of serviceread2026-07-25
The gpt-oss USAGE_POLICY is complete in two sentences: "We aim for our tools to be used safely, responsibly, and democratically, while maximizing your control over how you use them.
Third-party analysisunverified2026-07-25
Hugging Face's launch guide documents day-0 gpt-oss support across transformers, vLLM, Ollama and llama.cpp, the native MXFP4 quantization, and the harmony format.
Documentationunverified2026-07-25
gpt-oss is trained for OpenAI's harmony response format (role hierarchy and separate reasoning/tool/final channels), rendered via the openai/harmony library.
Securityread2026-07-25
The OpenAI gpt-oss safety report PDF describes adversarial malicious-fine-tuning on bio/cyber data to simulate a worst case (with external reviewers METR, SecureBio, Daniel Kang).
Third-party analysisread2026-07-25
METR's third-party methodology review of OpenAI's gpt-oss malicious-fine-tuning safety work states "OpenAI at least partially addressed each of our 6 high-urgency items," while flagging that no published High-capability criteria exist.
Third-party analysisunverified2026-07-25
gpt-oss ranks strongly among open-weight models on independent public leaderboards.
Documentationunverified2026-07-25
The openai/gpt-oss reference repository provides implementations, serving guidance and fine-tuning references for the open weights.
Model cardread2026-11-19
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b (created 2025-09-18) are separate OpenAI safety-classification fine-tunes of gpt-oss.
Third-party analysisunverified2026-07-25
gpt-oss is available in the Ollama model library for local single-command serving.