Nemotron 3 Nano Omni — local AI model by NVIDIA

Written by Jakub Rusinowski · Last updated

The first mainstream omni-modal open model that a single consumer GPU can actually hold: text, image, speech and video in, text out, at 3B active parameters from a 30B MoE. 260K context under the NVIDIA Open Model License, which permits commercial use. The efficiency ratio here is the story — video understanding at roughly the per-token cost of a 3B dense model.

NVIDIA Blog Hugging Face

Variants

The smallest Nemotron 3 Nano Omni variant needs about 19 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.

ModelVRAM
Nemotron 3 Nano Omni 30B-A3B →
30B/3B active
~18.9 GB

Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.

How to run Nemotron 3 Nano Omni locally

Install Ollama, then pull the tag.

ollama run nemotron-3-nano-omni

Pick a size above for its own VRAM figure, speed estimate and install command.

Licence

NVIDIA Open Model LicenseCommercial use permitted

Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

Applies to: Nemotron 3 Nano Omni 30B-A3B

Recommended GPU

The cheapest catalogued GPU that runs Nemotron 3 Nano Omni locally (min 19 GB VRAM) is the AMD Radeon RX 7900 XTX (24 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
AMD Radeon RX 7900 XTX 24GB
24 GB VRAM · 355 W board power
2026 prices are volatile — check the current listing.

Can I run Nemotron 3 Nano Omni on my GPU?

Nemotron 3 Nano Omni — frequently asked questions

How much VRAM does Nemotron 3 Nano Omni need?

Nemotron 3 Nano Omni needs about 19 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Nemotron 3 Nano Omni 30B-A3B (19 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run Nemotron 3 Nano Omni on an RTX 4090 (24 GB)?

Yes — Nemotron 3 Nano Omni runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for Nemotron 3 Nano Omni?

Q4_K_M is the best balance of quality and VRAM for Nemotron 3 Nano Omni in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run Nemotron 3 Nano Omni with Ollama?

Nemotron 3 Nano Omni has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.