← Back to models

OpenReasoning-Nemotron

NVIDIA (USA) July 19 2025

Parameters

1.5B / 8B / 32B (3 sizes; dense)

License

Apache 2.0

Key Features

Distilled reasoning suite from DeepSeek R1-0528; SOTA in math/science/code (GPQA, MMLU-PRO, AIME 2025); tops LiveCodeBench/SciCode; supports TensorRT-LLM/NeMo integration; optimized for Hugging Face Transformers and ONNX deployment; commercially permissive.