Nemotron-Cascade-2-30B-A3B

Introduction

We're excited to introduce Nemotron-Cascade-2-30B-A3B, an open 30B MoE model with 3B activated parameters that delivers strong reasoning and agentic capabilities. It is post-trained from the Nemotron-3-Nano-30B-A3B-Base. Nemotron-Cascade-2-30B-A3B achieves gold medal performance in both the 2025 International Mathematical Olympiad (IMO) and the International Olympiad in Informatics (IOI). It operates in both thinking and instruct (non-thinking) modes.

Quick Start

• Nemotron-Cascade-2-30B-A3B follows the ChatML template and supports both thinking and instruct (non-thinking) modes. Reasoning content is enclosed within <think> and </think> tags. To activate the instruct (non-thinking) mode, They prepend <think></think> to the beginning of the assistant’s response.
• Nemotron-Cascade-2-30B-A3B does not currently support OpenCode; it primarily supports OpenHands for agentic coding and SWE tasks.
• To reduce the context length in a multi-turn conversation, when the previous user turn involves thinking mode, only the final summary of the model's output will be added to the conversation history.
• Note that we do not define a separate tool role for tool responses; instead, we place them under the user role and wrap them with <tool_response> and </tool_response>.
• We recommend setting the sampling parameters to temperature = 1.0 and top_p = 0.95.

License

Your use of this model is governed by the NVIDIA Open Model License.