NVIDIA Nemotron 3 Nano Omni — Specifications
Compiled by Mustafa Ihsan from the vendor’s published documentation · Last updated
| Developer | NVIDIA |
|---|---|
| Type | Multimodal (omni) |
| Modality | Text, Image, Audio, Video → Text |
| Parameters | 31B total / ~3B active (MoE) |
| Context window | 256K |
| License | NVIDIA Open Model Agreement |
| Open weights | Yes |
| Released | 2026-04 |
| API providers | Hugging Face, OpenRouter, NVIDIA NIM |
Run it locally
| VRAM (FP16/BF16) | ~62 GB |
|---|---|
| VRAM (4-bit) | ~21 GB (NVFP4) |
| Minimum GPU | RTX 5090 32GB (NVFP4) / H100 80GB (BF16) |
Benchmarks
| OCRBench V2 | 67.04 |
|---|---|
| Video-MME | 72.2 |
| OSWorld | 47.4 |
| Speech IF | 89.39 |
What is NVIDIA Nemotron 3 Nano Omni?
NVIDIA Nemotron 3 Nano Omni is an open omni-modal model: it sees, hears, watches and reads (text, image, audio and video in, text out) from a single mixture-of-experts model with 31B total parameters that activates about 3B per token. NVIDIA released it on 28 April 2026. It is a Mamba2-Transformer hybrid with a context of up to 256K tokens, released under the NVIDIA Open Model Agreement, which permits commercial use. NVIDIA’s model card reports 67.04 on OCRBench V2 (English), 72.2 on Video-MME, 47.4 on OSWorld and 89.39 on Speech IF.
Four input modalities in one model that runs on a single GPU is the notable part. NVIDIA lists one RTX 5090 32GB as the minimum for the NVFP4 checkpoint (about 21 GB) and one H100 80GB for BF16. The usual way to build an application that handles audio, video, images and text is to chain three or four specialist models, each with its own deployment, latency budget and failure mode. Nemotron 3 Nano Omni collapses that into one, which is why its 47.4 on OSWorld, a computer-use benchmark that requires seeing a screen and acting on it, is more interesting than the raw number suggests. NVIDIA publishes no per-token API price; the cost is the hardware. NVIDIA’s newer Nemotron 3.5 Super VL (15 October 2026) takes text, images and video but not audio. More background in our Nemotron 3 Nano Omni explainer.
NVIDIA Nemotron 3 Nano Omni pricing
NVIDIA Nemotron 3 Nano Omni has no public per-token API price. It is open-weight, so the only cost is the hardware you run it on — see the local-hardware table above and size a GPU with the VRAM calculator.
