ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
OpenAI
GPT-OSS-20B
Model
OpenAI
GPT-OSS-20B

OpenAI releases the gpt-oss family of open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

NVIDIA AI Enterprise SupportedNVIDIA NIM
NameSizeUpdatedActions
chat_template.jinja
14.22 KBAugust 5, 2025 UTC
chat_template.json
14.95 KBAugust 5, 2025 UTC
checksums.blake3
989 BAugust 5, 2025 UTC
config.json
1.76 KBAugust 5, 2025 UTC
generation_config.json
165 BAugust 5, 2025 UTC
model-00000-of-00002.safetensors
4.46 GBAugust 5, 2025 UTC
model-00001-of-00002.safetensors
4.47 GBAugust 5, 2025 UTC
model-00002-of-00002.safetensors
3.88 GBAugust 5, 2025 UTC
model.safetensors.index.json
35.5 KBAugust 5, 2025 UTC
special_tokens_map.json
98 BAugust 5, 2025 UTC
tokenizer_config.json
4.1 KBAugust 5, 2025 UTC
tokenizer.json
26.58 MBAugust 5, 2025 UTC

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.