Language

NVIDIA Nemotron 3.5 Lightning 30B-A3B (MoE)

NVIDIA Nemotron 3.5 Lightning — 30B total / 3B active hybrid Mamba-2 + Attention MoE. Thinking + instruct, 256K native context extensible to ~1M. Single-file GGUF, single-node serving.

OpenMDW-1.1Source verified

Specification

Model ID

nemotron-3.5-lightning-30b-a3b

Family

nemotron-lightning

Modality

Language

Parameters

30B (MoE, 3B active)

Context

262,144 tokens

Quantization

UD-Q4_K_XL

Weights

23.7 GB

Minimum RAM

32 GB

Source

Weights and provenance.

Repository

unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF

Registry license

OpenMDW-1.1

Source license

other

Access

Open — weights fetch without accepting additional terms.

The registry records this model as OpenMDW-1.1 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-3.5-lightning-30b-a3b

# Serve it
tenzro model serve nemotron-3.5-lightning-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-3.5-lightning-30b-a3b"}]}'

← All models