Language

Nemotron 3 Nano 4B

Hybrid Mamba-2 + Attention edge model, 256K context

NVIDIA OpenSource verified

Specification

Model ID

nemotron-nano-4b

Family

nemotron

Modality

Language

Parameters

Context

262,144 tokens

Quantization

Q4_K_M

Weights

2.7 GB

Minimum RAM

4 GB

Source

Weights and provenance.

Repository

unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF

Registry license

NVIDIA Open

Access

Open — weights fetch without accepting additional terms.

The licence above is the registry's. The source repository either states nothing, states the catch-all “other”, or carries a licence link and base model that its own tag contradicts — a re-quantisation inherits the terms of the weights it derives from. The registry's licence is the one to rely on.

Serve it

# Pull the weights onto a node
tenzro model download nemotron-nano-4b

# Serve it
tenzro model serve nemotron-nano-4b

# 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-nano-4b"}]}'

Same family

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

30B (MoE, 3B active)

Nemotron 3 Ultra 550B-A55B (MoE)

550B (MoE, 55B active)

Nemotron 3 Nano 30B-A3B (MoE)

30B (MoE, 3B active)

← All models