ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Container
NVIDIA
NVIDIA
Nemotron-3-Nano-Omni-30B-A3B-Reasoning

Nemotron Nano V3 Omni is a multi-modal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.

NVIDIA AI Enterprise SupportedNVIDIA NIM
LayerLabelCreated
b5035b80ac0c0e70e350280d1339c3a4fb41160e56471fc0fbcb611c313d7737CONFIG
Entrypoint /bin/bash /opt/nim/start_server.sh; WorkingDir /opt/nim
04/27/2026 7:29 PM UTC
a69317b82de7d5c6b4ac77e7a4816839f5d04791891b52b20553a88eec9f3e13COPY
--chmod=755 ./start_server.sh /opt/nim/start_server.sh
04/27/2026 7:29 PM UTC
1f046b864560647beef8f1d95a5b8b396063c4ac42bb56620764362f81d8d99fENV
FLASHINFER_LOGGING_LEVEL=ERROR
04/27/2026 7:29 PM UTC
44187efd784fb82f20db636599c32724f4d08879ac25ae9084de7ff4fe5781e9ENV
NCCL_P2P_DISABLE=1
04/27/2026 7:29 PM UTC
4105d3133c6735cf1d34d89579ed33eeb5562fd6ac6396d1c1874df25bf890faENV
VLLM_WORKER_MULTIPROC_METHOD=spawn
04/27/2026 7:29 PM UTC
e5fcd334eeb8a6054d36f3a77bfccfe47d0d9ba5e69cbd1b91f6883a0341f3d4ENV
VLLM_USE_FLASHINFER_MOE_FP16=0
04/27/2026 7:29 PM UTC
9fb3497de28ef9a83473a0981555256060a967fc0d5f254d793675485e75485eENV
NIM_MAX_NUM_SEQS=256
04/27/2026 7:29 PM UTC
4f69839c672aec2745ab4bec94455b0577da6a0e5b4aba6da0c4a931c7bec7faENV
NIM_VIDEO_PRUNING_RATE=0.50
04/27/2026 7:29 PM UTC
5a568735d3c4859987773693fd40f5f166c4e67dff0bfa0801ea60b594b7a78dENV
NIM_MEDIA_IO_KWARGS={"video": {"fps": 2, "num_frames": 512}}
04/27/2026 7:29 PM UTC
4f27d3d22e59bf2270960bee2d39906bdecdc13e2a0ae241972394f24f92a576ENV
NIM_REASONING_PARSER=nemotron_v3
04/27/2026 7:29 PM UTC
...

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.