Openreasoning Nemotron 32B
NVIDIA's OpenReasoning Nemotron 32B is a large language model designed for reasoning tasks, particularly exceling in generating solutions for math, code, and science problems. It is notable for its ability to handle up to 64K output tokens, demonstrating its capacity for complex and lengthy responses.
Input
Output
Context
66K
Max Output
66K
Parameters
32B
Technical Specifications
Model TypeChat
Context Window65,536 tokens
Max Output Tokens65,536 tokens
Parameters32B
Release DateJul 15, 2025
Training CutoffFeb 1, 2025
Licensecc-by-4.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Openreasoning Nemotron 32B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.