NVIDIA

Multimodal model · United States ·Apr 2026

NVIDIA Nemotron 3 Nano Omni

Multimodal Open Weights

31.6B

Parameters

256K

Context

Benchmarks

About NVIDIA Nemotron 3 Nano Omni

NVIDIA Nemotron 3 Nano Omni is an AI model developed by NVIDIA, in the multimodal category, released in 2026, made available as an open-weights model with 31.6B params. Nemotron 3 Nano Omni is an open 30B-A3B hybrid Mixture-of-Experts model unifying vision, audio, image, and text input wi.

On this page you'll find NVIDIA Nemotron 3 Nano Omni's full specifications, including a context window of 256K tokens, 3 benchmark results. Review provider pricing and benchmark scores below, or compare NVIDIA Nemotron 3 Nano Omni head-to-head with other multimodal models.

→ More models by NVIDIA → All multimodal models → AI benchmarks leaderboard

Links

Paper ↗

Run NVIDIA Nemotron 3 Nano Omni locally — what to buy

Share this build ↗

Sized to what NVIDIA Nemotron 3 Nano Omni actually needs (~256k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good

AMD Radeon RX 7900 XTX

Consumer GPU · ~$999

~41.8 tok/s

Q4 · fits full context · up to 11k ctx

Runs with: ExLlamaV2, KoboldCpp, LM Studio

See full estimate →

Better

NVIDIA GeForce RTX 4090

Consumer GPU · ~$1,599

~49.6 tok/s

Q4 · fits full context · up to 11k ctx

Runs with: ExLlamaV2, KoboldCpp, LM Studio

See full estimate →

Best

NVIDIA GeForce RTX 5090

Consumer GPU · ~$1,999

~88.1 tok/s

Q4 · fits full context · up to 39k ctx

Runs with: ExLlamaV2, KoboldCpp, LM Studio

See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Community

Would you run NVIDIA Nemotron 3 Nano Omni again?

No votes yet — be the first.

Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

NVIDIA Nemotron 3 Nano Omni benchmark scores▶

Compare on the benchmark table →

Benchmark	Category	Score
VoiceBench	general	89.4%
MathVista	multimodal	82.8%
Video-MME	multimodal	72.2%

More models like NVIDIA Nemotron 3 Nano Omni

NeuroChess

· 72.3K

NVIDIA Nemotron 3.5 ASR Streaming 0.6B

NVIDIA · 600M

NVIDIA Nemotron 3 Ultra

NVIDIA · 550B

NVIDIA Nemotron 3.5 Content Safety

Frequently asked questions

What is NVIDIA Nemotron 3 Nano Omni? ▶

Nemotron 3 Nano Omni is an open 30B-A3B hybrid Mixture-of-Experts model unifying vision, audio, image, and text input wi It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created NVIDIA Nemotron 3 Nano Omni? ▶

NVIDIA Nemotron 3 Nano Omni was developed by NVIDIA and released in 2026.

Is NVIDIA Nemotron 3 Nano Omni open source or proprietary? ▶

NVIDIA Nemotron 3 Nano Omni ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

What is NVIDIA Nemotron 3 Nano Omni's context window? ▶

NVIDIA Nemotron 3 Nano Omni supports a context window of 256K tokens, and has 31.6B params.

How much does NVIDIA Nemotron 3 Nano Omni cost? ▶

Pricing for NVIDIA Nemotron 3 Nano Omni depends on the provider. See the providers table on this page for the latest API rates.

How does NVIDIA Nemotron 3 Nano Omni perform on benchmarks? ▶

NVIDIA Nemotron 3 Nano Omni is benchmarked across 3 evaluations on GenAIList, including VoiceBench (89.4%). See the full benchmark table below and compare it with other models.