Latest Content
Nemotron 3 Nano Omni 30B A3B Reasoning BF16 icon

Nemotron 3 Nano Omni 30B A3B Reasoning BF16

NVIDIA
Nvidia Nemotron 3 Nano Omni 30B A3B Reasoning BF16 is a multimodal Mixture-of-Experts reasoning model designed for unified audio, vision, and language understanding, enabling AI agents to efficiently derive insights from videos and documents with high accuracy. It features a 30B parameter architecture with 3B activated, using 52 layers, 2,688 hidden size, and 32 attention heads, activating 6 experts per token across 128 routed experts with a shared expert. The model integrates C-RADIOv4-H based vision and Parakeet audio encoders, and combines hybrid Mamba-attention layers for efficient long-context processing and precise reasoning, supporting up to 256K tokens for image, video, document, and speech reasoning tasks.
TypeOmni Model
CapabilitiesText Generation, Instruction Following, Reasoning, Mathematical Reasoning+7 more
Release Date28 April, 2026
Links
Blog|HF Model Card
LicenseNVIDIA Open Model Agreement

Inference Instructions

Deploy and run this model on NVIDIA B200 GPUs using the command below. Copy the command to get started with inference.

CONSOLE
docker run -it --rm 
 --runtime=nvidia 
 --gpus all 
 --ipc=host 
 --shm-size=128g 
 -p 8000:8000 
 -v ~/.cache/huggingface:/root/.cache/huggingface 
 -v $(pwd)/super_v3_reasoning_parser.py:/plugins/super_v3_reasoning_parser.py 
 -e HF_TOKEN='YOUR_HF_TOKEN' 
 vllm/vllm-openai:v0.20.0 
 nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 
  --tensor-parallel-size 8 
 --max-model-len auto 
 --max-num-batched-tokens 65536 
  --gpu-memory-utilization 0.96 
  --max-num-seqs 1024 
  --max-cudagraph-capture-size 512 
 --enable-auto-tool-choice 
 --tool-call-parser qwen3_coder 
 --reasoning-parser-plugin=/plugins/super_v3_reasoning_parser.py 
 --reasoning-parser super_v3 
 --trust-remote-code
Note

Download reasoning parser before serving: wget "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8/resolve/main/super_v3_reasoning_parser.py" and pass --reasoning-parser-plugin "/plugins/super_v3_reasoning_parser.py" --reasoning-parser super_v3

Model Benchmarks

Each model was tested with a fixed input size and total token volume while increasing concurrency to measure serving performance under load.

ITL vs Concurrency

Time to First Token

Throughput Scaling

Total Tokens/sec vs Avg TTFT

Vultr Cloud GPU

NVIDIA HGX B200

Deploy NVIDIA B200 on Vultr Cloud GPU

Deploy NVIDIA B200 instancesContact Sales