Chat

Apache 2.0Open weightsUpdated June 2026Frontier 2026

gpt-oss-120b

Larger gpt-oss model for users evaluating high-capacity open-weight deployments.

OpenAI · gpt-oss

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedJune 2026SourcesOpenAI, Hugging Face

Model checkpoints, context windows, provider support, local runtime compatibility, and license terms can change quickly. Verify the exact model card before production or commercial use.

Best for

Teams evaluating high-capacity local, self-hosted, or developer-controlled model deployments.

Who should use it

  • Teams evaluating high-capacity local, self-hosted, or developer-controlled model deployments.
  • Builders who want local or self-hosted testing options.

Common workflows

  • High-capacity open-weight deployment evaluation
  • open weights workflows
  • local workflows
  • self-hosted workflows
  • developer-controlled workflows

Deployment and hardware notes

Expect server-class requirements for full-weight deployment; use hosted or quantized options where available.

License and usage notes

Apache 2.0. Open weights. Verify the exact model card and license terms for the checkpoint or hosted provider you use.

Strengths

  • Open weights model option for gpt-oss workflows.
  • Teams evaluating high-capacity local, self-hosted, or developer-controlled model deployments.
  • Best evaluated with the exact release, runtime support, and hardware profile available to your team.
  • Tracked as Frontier 2026 in the OpenSourcesAI model directory.

Limitations

  • Larger open-weight models require careful license review, serving support, hardware planning, and evaluation on your own workloads.
  • Expect server-class requirements for full-weight deployment; use hosted or quantized options where available.
  • Context window and limits: 131,072 tokens, confirmed from the model's published config.
  • Verify the exact model card, provider docs, license, and serving support before production use.

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

Frontier-model verification note

This page is written to stay accurate as of the latest available 2026 public model information. Availability, licenses, context windows, API support, pricing, benchmark standing, and local-serving support can change quickly. Verify the official model card, provider docs, and license before using this model in production or commercial workflows.

Sources to verify

OpenAIHugging Face

Related resources

Continue with model source notes, local tools, and implementation guides related to this model.

gpt-oss family hubBest local LLM toolsPrivate local chatbot stackOllama + Open WebUI starter stackAI tools directory
HardwareServer-classRuntimevLLM, Transformers, hosted providers where supportedContext131,072 tokens, confirmed from the model's published configLast updated2026
OpenAI →

Model ecosystem connections

Use these next-step links to move from this profile into related tools, comparisons, guides, stacks, and curated shortlists.

Recommended runtimes and tools

Transformers →vLLM →Ollama →LM Studio →llama.cpp →

Setup and deployment

What is quantization? GGUF, Q4, Q8 explained →RunPod — managed GPU cloud →Lambda Labs — A100 / H100 on demand →Vast.ai — crowdsourced GPU marketplace →

Related model pages

gpt-oss family hub →gpt-oss-20b →Llama 3.1 405B Instruct →DeepSeek V3 →Gemma 2 27B Instruct →Gemma 2 9B Instruct →Gemma 3 27B →

Guides, stacks, and comparisons

Best local LLM tools →Private local chatbot stack →Ollama + Open WebUI starter stack →All model comparisons →

Related models

gpt-oss-20bBuilders evaluating more accessible open-weight deployments for local apps, prototypes, and controlled workflows.Llama 3.1 405B InstructServer-class assistant evaluation and comparisons against smaller Llama variants.DeepSeek V3General DeepSeek-family comparisons and assistant workflow evaluation.Gemma 2 27B InstructEfficient local prototypes, app workflows, and Gemma-family comparisons.Gemma 2 9B InstructEfficient local prototypes, app workflows, and Gemma-family comparisons.Gemma 3 27BDevelopers testing capable medium-sized chat models with broad tooling support.

Ready to run this model locally?

Find a compatible interface in our Local AI Tools directory →