Language

Nemotron 3 Nano Omni 30B-A3B (MoE, multimodal)

NVIDIA Nemotron 3 Nano Omni — 30B total / 3B active hybrid reasoning MoE, 256K context. Accepts audio, video, text, images and documents; output is text. Needs a llama.cpp-compatible backend: the vision path uses a separate mmproj file that Ollama does not load.

NVIDIA OpenSource verified

Specification

Model ID

nemotron-3-nano-omni-30b-a3b

Family

nemotron

Modality

Language

Parameters

30B (MoE, 3B active)

Context

262,144 tokens

Quantization

UD-Q4_K_XL

Weights

17.2 GB

Minimum RAM

25 GB

Source

Weights and provenance.

Repository

unsloth/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF

Registry license

NVIDIA Open

Source license

other

Access

Open — weights fetch without accepting additional terms.

The registry records this model as NVIDIA Open while the source repository states other. Both are shown here rather than one being preferred. Treat the stricter of the two as binding until the discrepancy is resolved upstream.

Serve it

# Pull the weights onto a node
tenzro model download nemotron-3-nano-omni-30b-a3b

# Serve it
tenzro model serve nemotron-3-nano-omni-30b-a3b

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"nemotron-3-nano-omni-30b-a3b"}]}'

Same family

Nemotron 3 Ultra 550B-A55B (MoE)

550B (MoE, 55B active)

Nemotron 3 Nano 30B-A3B (MoE)

30B (MoE, 3B active)

Nemotron 3 Nano 4B

← All models