--- library_name: transformers license: other license_name: nvidia-open-model-license license_link: >- https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ pipeline_tag: text-generation language: - en tags: - nvidia - nemotron-cascade-2 - reasoning - general-purpose - SFT - RL --- # Nemotron-Cascade-2-30B-A3B

[![Technical Report](https://img.shields.io/badge/2603.19220-Technical_Report-blue)](https://arxiv.org/abs/2603.19220) [![SFT Dataset](https://img.shields.io/badge/🤗-SFT_Datset-blue)](https://huggingface.co/datasets/nvidia/Nemotron-Cascade-2-SFT-Data) [![RL Dataset](https://img.shields.io/badge/🤗-RL_Datset-blue)](https://huggingface.co/datasets/nvidia/Nemotron-Cascade-2-RL-data) [![Models](https://img.shields.io/badge/🤗-Models-blue)](https://huggingface.co/collections/nvidia/nemotron-cascade-2)

main_fig ## Introduction We're excited to introduce [Nemotron-Cascade-2-30B-A3B](https://huggingface.co/nvidia/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](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16). 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. ## Benchmark Results
Benchmark Nemotron-3-Nano-30B-A3B Nemotron-3-Super-120B-A12B Qwen3.5-35B-A3B Nemotron-Cascade-2-30B-A3B
Math
IMO 2025 ---🏅 35 pts
IMO AnswerBench 70.4‡77.2‡74.8‡79.3
IMO ProofBench ---72.9
AIME 2025 89.190.291.9‡92.4 (98.6)†
AIME 2026 89.9‡89.8‡91.1‡90.9 (95.0)†
HMMT Feb25 84.6‡93.789.094.6
Code Reasoning
IOI 2025 --348.6‡🏅 439.3
ICPC World Finals 2025 ---🏅 10/12
LiveCodeBench v6 (2408-2505) 68.378.774.687.2 (88.4)†
LiveCodeBenchPro 25Q2 (Easy) 54.5‡81.7‡81.1‡87.0 (89.3)†
LiveCodeBenchPro 25Q2 (Med) 3.50‡23.2‡17.8‡27.6 (36.8)†
SciCode 33.342.138.036.4
Knowledge & STEM
MMLU-Redux --93.386.3
MMLU-Pro 78.383.785.379.8
GPQA-Diamond 73.079.284.276.1
HLE (no tool) 10.618.322.417.7
Alignment & Instruction Following
ArenaHard v2 (Avg.) 67.7-65.4‡83.5
  – Hard Prompt 72.173.964.5‡88.2
  – Creative Writing 63.2-66.3‡78.7
IFBench (prompt) 71.572.670.282.9
Scale AI Multi-Challenge 38.555.260.045.3
Long Context & Context Learning
AA-LCR 35.958.358.539.1
LongBench v2 39.6-59.040.3
NIAH@1M (RULER Subset) 94.898.394.3‡99.0
CL-Bench 12.0‡-15.5‡12.2
Agentic
BFCL v4 53.8-67.352.9
𝜏²-Bench 49.061.281.258.9
Terminal Bench 2.0 8.531.040.521.1
SWE Verified (OpenHands) 38.860.569.250.2
Multilingual
MMLU-ProX 59.579.481.072.5
WMT24++ (en -> xx) 86.286.787.6‡84.1

* † Numbers in brackets refers to Tool-Integrated Reasoning (TIR) results.
* ‡ For the baseline models, we evaluate them using the recommended settings when official numbers are unavailable; otherwise, we report the official numbers directly.

## 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 `` and `` tags. To activate the instruct (non-thinking) mode, we prepend `` to the beginning of the assistant’s response. - Nemotron-Cascade-2-30B-A3B supports up to a 1M-token context length. - 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 warp them with `` and ``. - We recommend setting the sampling parameters to temperature = 1.0 and top_p = 0.95. ### vLLM setup Requires vLLM version >= 0.17.1. The following will create API endpoints at `http://localhost:8000/v1`: - **Standard version**: Use the following command to create an API endpoint with a maximum context length of 1M tokens. ```shell vllm serve nvidia/Nemotron-Cascade-2-30B-A3B --port 8000 --tensor-parallel-size 1 --gpu-memory-utilization 0.9 --max-model-len 262144 --reasoning-parser nemotron_v3 --mamba-ssm-cache-dtype float32 --port 8000 --trust_remote_code ``` - **Tool Call**: Use the following command to enable tool support. ```shell vllm serve nvidia/Nemotron-Cascade-2-30B-A3B --port 8000 --tensor-parallel-size 1 --gpu-memory-utilization 0.9 --max-model-len 262144 --reasoning-parser nemotron_v3 --mamba-ssm-cache-dtype float32 --port 8000 --trust_remote_code --enable-auto-tool-choice --tool-call-parser qwen3_coder ``` ### Chat Template ```python from transformers import AutoTokenizer model_name = 'nvidia/Nemotron-Cascade-2-30B-A3B' tokenizer = AutoTokenizer.from_pretrained(model_name) ''' single-turn example ''' messages = [ {"role": "system", "content": "You are a helpful and harmless assistant.\n\nYou are not allowed to use any tools"}, {"role": "user", "content": "calculate 1+1?"} ] # thinking mode prompt_thinking = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True) # prompt_thinking = '<|im_start|>system\nYou are a helpful and harmless assistant.\n\nYou are not allowed to use any tools<|im_end|>\n<|im_start|>user\ncalculate 1+1?<|im_end|>\n<|im_start|>assistant\n\n' # instruct mode prompt_instruct = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) # prompt_instruct = '<|im_start|>system\nYou are a helpful and harmless assistant.\n\nYou are not allowed to use any tools<|im_end|>\n<|im_start|>user\ncalculate 1+1?<|im_end|>\n<|im_start|>assistant\n' ''' multi-turn example ''' messages = [ {"role": "system", "content": "You are a helpful and harmless assistant.\n\nYou are not allowed to use any tools"}, {"role": "user", "content": "calculate 1+1?"}, {"role": "assistant", "content": "THINKING_CONTENT\nTo calculate \\(1 + 1\\):\n\n1. **Identify the operation**: This is a basic addition problem involving two integers.\n2. **Perform the addition**: \n \\(1 + 1 = 2\\).\n\n**Result**: \\(\\boxed{2}\\)",}, {"role": "user", "content": "what about 2+2"} ] # thinking mode prompt_thinking = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True) # prompt_thinking = '<|im_start|>system\nYou are a helpful and harmless assistant.\n\nYou are not allowed to use any tools<|im_end|>\n<|im_start|>user\ncalculate 1+1?<|im_end|>\n<|im_start|>assistant\n\nTo calculate \\(1 + 1\\):\n\n1. **Identify the operation**: This is a basic addition problem involving two integers.\n2. **Perform the addition**: \n \\(1 + 1 = 2\\).\n\n**Result**: \\(\\boxed{2}\\)<|im_end|>\n<|im_start|>user\nwhat about 2+2<|im_end|>\n<|im_start|>assistant\n\n' # instruct mode prompt_instruct = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) # prompt_instruct = '<|im_start|>system\nYou are a helpful and harmless assistant.\n\nYou are not allowed to use any tools<|im_end|>\n<|im_start|>user\ncalculate 1+1?<|im_end|>\n<|im_start|>assistant\n\nTo calculate \\(1 + 1\\):\n\n1. **Identify the operation**: This is a basic addition problem involving two integers.\n2. **Perform the addition**: \n \\(1 + 1 = 2\\).\n\n**Result**: \\(\\boxed{2}\\)<|im_end|>\n<|im_start|>user\nwhat about 2+2<|im_end|>\n<|im_start|>assistant\n' ``` ### Python Tool Use ```python model_name = 'nvidia/Nemotron-Cascade-2-30B-A3B' tokenizer = AutoTokenizer.from_pretrained(model_name) SYSTEM_PROMPT = """# Tools You have access to the following functions: stateful_python_code_exec Call this function to execute Python code in a stateful Jupyter notebook environment. Python will respond with the output of the execution or time out after 120.0 seconds. code string Code to execute ["code"] If you choose to call a function ONLY reply in the following format with NO suffix: value_1 This is the value for the second parameter that can span multiple lines Reminder: - Function calls MUST follow the specified format: an inner block must be nested within XML tags - Required parameters MUST be specified - You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after - If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls """ messages = [ {"role": "system", "content": SYSTEM_PROMPT}, {"role": "user", "content": "Solve the following math problem. Put your answer inside \\boxed{}.\n\nIn a school with 2008 students, each student is a member of certain committees. Each committee has at most 1004 members, and every two students are in at least one common committee. Determine the smallest possible number of committees in the school."} ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True) print(prompt) ``` ### Agentic Usage ```python model_name = 'nvidia/Nemotron-Cascade-2-30B-A3B' tokenizer = AutoTokenizer.from_pretrained(model_name) SYSTEM_PROMPT = """You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the and tags. In each turn you can either: - Send a message to the user. - Make a tool call. You cannot do both at the same time. _NEED_TO_ADD_POLICY_HERE_ Try to be helpful and always follow the policy. # Tools You have access to the following functions: _NEED_TO_ADD_FUNCTION_NAME_1_ _FUNCTION_DESCRIPTION_ _NEED_TO_ADD_PARAMETER_NAME_1_ _PARAMETER_TYPE_ _PARAMETER_DESCRIPTION_ _PARAMETER_TITLE_ _NEED_TO_ADD_PARAMETER_NAME_2_ _PARAMETER_TYPE_ _PARAMETER_DESCRIPTION_ _PARAMETER_TITLE_ ...... (_MORE_PARAMETERS_TO_ADD_) ...... (_MORE_FUNCTIONS_TO_ADD_) """ messages = [ {"role": "system", "content": SYSTEM_PROMPT}, {"role": "user", "content": "Hello, I'm calling regarding my upcoming stay at your hotel. My guest ID is G90920 and booking ID is B11246 for a Deluxe room on June 5th. I'm traveling with three 6-month-old triplets and need to request three infant cribs for our room. It's currently 30 hours before check-in—could you please confirm if this is feasible and if there are quiet room options available for families with infants?"} ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True) print(prompt) ``` ## Release Date Mar 19, 2026 ## License Your use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). ## Citation ``` @article{Nemotron_Cascade_2, title={Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation}, author={Yang, Zhuolin and Liu, Zihan and Chen, Yang and Dai, Wenliang and Wang, Boxin and Lin, Sheng-Chieh and Lee, Chankyu and Chen, Yangyi and Jiang, Dongfu and He, Jiafan and Pi, Renjie and Lam, Grace and Lee, Nayeon and Bukharin, Alexander and Shoeybi, Mohammad and Catanzaro, Bryan and Ping, Wei}, year={2026} } ```