{"id":"nvidia/nvidia-nemotron-3-super-120b-a12b-fp8","aliases":["hf:nvidia/nvidia-nemotron-3-super-120b-a12b-fp8","nvidia/nemotron-3-super-120b-a12b","nvidia/nemotron-3-super-120b-a12b-20230311","nvidia/nemotron-3-super-120b-a12b:free","openrouter:nvidia/nemotron-3-super-120b-a12b","openrouter:nvidia/nemotron-3-super-120b-a12b:free"],"displayName":"NVIDIA: Nemotron 3 Super","author":"nvidia","createdAt":"2026-03-11T16:07:19.000Z","updatedAt":"2026-09-08T17:00:59.308Z","popularityRank":83,"metadata":{"modalities":["text"],"inputModalities":["text"],"outputModalities":["text"],"contextLength":1000000,"maxOutputTokens":16384,"family":"nemotron","modelsDev":{"provider":"openrouter","sourceUrl":"https://models.dev/api.json","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","lastUpdated":"2026-03-11","releaseDate":"2026-03-11","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"temperature":true,"open_weights":true,"structured_output":true}},"tokenizer":"Other","licenseStatus":"unknown","weightsAvailable":false,"hostedInferenceAllowed":false,"gated":false,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"providerNames":[],"isModerated":false},"availability":"unknown","externalBest":null,"multivibeNetwork":null,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","runtimes":[],"protocols":[],"harnesses":[]}