Model reference · open weights
Nemotron-3-Nano-Omni-Reasoning is an open-weight language model from nvidia, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
At a Glance Quick Start Guide Model Parameters Model Overview Description: NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows. It extends the Nemotron Nano family with integrated video+speech comprehension, Graphical User Interface (GUI), Optical Character Recognition (OCR), and speech transcription capabilities, enabling end-to-end processing of rich enterprise content such as meeting recordings, M&E assets, training videos, and complex business documents. NVIDIA Nemotron 3 Nano Omni was developed by NVIDIA as part of the Nemotron model family. <br This model is available for commercial use. <br This model was improved using Qwen3-VL-30B-A3B-Instruct, Qwen3.5-122B-A10B, Qwen3.5-397B-A17B, Qwen2.5-VL-72B-Instruct, and gpt-oss-120b. For more information, please see the Training Dataset section below. <br License/Terms of Use Governing Terms: Use of this model is governed by the NVIDIA Open Model Agreement<br Deployment Geography: Global <br Use Case: <br This model is designed for enterprise customers requiring multimodal understanding capabilities. Expected users include: - Customer service applications (e.g., Doordash video of drop-off at a given address via OCR, drive-thru order verification) - Media and Entertainment (M&E) — video and speech analysis, dense captions, video search and summarization - Document intelligence for AI assistants (contracts, SOW/MSA, scientific discovery, financial documents) - GUI automation for AI agentic applications (incident management, agentic search, browser agents, email agents) Release Date: <br Build.Nvidia.com 04/28/2026 via URL <br Hugging Face 04/28/2026 via: - BF16 <br - FP8 <br - NVFP4 <br NGC 04/28/2026 via URL <br Model Architecture: Architecture Type: Mamba2-Transformer Hybrid Mixture of Experts (MoE) <br Network Architecture: - Nemotron 3 Nano LLM (30B A3B) — 31B-parameter Mamba2-Transformer hybrid MoE backbone with ~3B active parameters per token. - CRADIO v4-H — vision encoder for image and video frames. - Parakeet — speech encoder for audio inpu
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | nvidia |
|---|---|
| Type | Language models |
| Parameters (lead) | 18.3B |
| Variants | 3 |
| Runs with | transformers |
| Based on | nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 |
| Released | 2026-04-24 |
| Popularity | 1.1M downloads / month |
| Likes | 422 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys nemotron-3-nano-omni-reasoning for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (nemotron-3-nano-omni-reasoning below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"nemotron-3-nano-omni-reasoning","messages":[{"role":"user","content":"Hello"}]}'
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗
Sources